© 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. 34-GEMMASCOPE-RES-131K
    7. 26011
    Prev
    Next
    INDEX
    Explanations

    not a

    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
    chromatic
    -0.96
    essentially
    -0.90
    something
    -0.89
    dsa
    -0.89
     τὰ
    -0.88
    somewhere
    -0.88
    ToOne
    -0.87
    摸了
    -0.87
    Beantwoorden
    -0.87
    another
    -0.86
    POSITIVE LOGITS
     a
    2.78
     sebuah
    0.94
     Even
    0.83
    восто
    0.81
     ersten
    0.79
    ophy
    0.77
    Ḳ
    0.77
     даже
    0.76
     een
    0.76
     Not
    0.76
    Activations Density 0.170%

    No Known Activations