© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112238
    Prev
    Next
    INDEX
    Explanations

    multilingual computing and technology contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    references to Karlsruhe or Telerik (specific proper nouns/brand names in technical contexts).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron flags distinctive proper‐name tokens—particularly organization, product, or place names (e.g. “Wikimedia,” “Telerik,” “Karlsruhe”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    了一
    -2.53
    </b>
    -2.44
    _
    -2.42
     oder
    -2.28
     или
    -2.27
    derdag
    -2.25
    ᡨ
    -2.22
     bzw
    -2.20
     Voraussetzung
    -2.20
     YOUR
    -2.19
    POSITIVE LOGITS
     kurzem
    3.03
     dritte
    2.81
     estavam
    2.56
    </strong>
    2.47
     jezt
    2.44
    </h3>
    2.42
     serão
    2.34
     hintergrund
    2.33
     trabalha
    2.30
     französische
    2.28
    Activations Density 0.000%

    No Known Activations