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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3668
    Prev
    Next
    INDEX
    Explanations

    Polish names, Nazi Germany, SQL, configurations

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

    The neuron activates on numeric tokens representing values greater than 100.

    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
     clín
    -2.52
    ן
    -2.50
     econó
    -2.42
     básicamente
    -2.34
     luchando
    -2.31
    fantasia
    -2.31
    麁
    -2.31
     fuertemente
    -2.30
     contoh
    -2.28
     ajouter
    -2.27
    POSITIVE LOGITS
     scrive
    2.64
    }$
    2.45
    as
    2.44
     et
    2.31
    and
    2.25
    榈
    2.20
    9
    2.20
    </em>
    2.17
     }
    2.16
     Fällen
    2.16
    Activations Density 0.001%

    No Known Activations