© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 32944
    Prev
    Next
    INDEX
    Explanations

    legal documents or code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Singleton
    -0.69
    観音
    -0.69
    父親
    -0.67
    仮想
    -0.66
     Silvia
    -0.65
     Trending
    -0.65
     Lansing
    -0.65
    rangle
    -0.63
    Serde
    -0.62
    inson
    -0.62
    POSITIVE LOGITS
    grama
    0.75
    暮
    0.73
    teva
    0.72
    handleError
    0.71
    whisky
    0.69
     quan
    0.68
    DaoImpl
    0.68
    yves
    0.67
    Metadata
    0.67
     towarzys
    0.66
    Activations Density 0.069%

    No Known Activations