© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58318
    Prev
    Next
    INDEX
    Explanations

    names followed by descriptors

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

    This neuron activates on capitalized single-word tokens that are proper nouns (e.g. names of places, companies, people, or other named entities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     حزب
    -1.45
    
    -1.38
    屋さん
    -1.38
    蟥
    -1.37
    歺
    -1.33
     unieke
    -1.31
     appeler
    -1.31
     Conferencia
    -1.30
     aanbod
    -1.29
    itif
    -1.25
    POSITIVE LOGITS
    Com
    1.26
    p
    1.17
    To
    1.16
    It
    1.13
    In
    1.10
    So
    1.10
    com
    1.09
    C
    1.09
     (
    1.05
    E
    1.05
    Activations Density 0.235%

    No Known Activations