© 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. 118098
    Prev
    Next
    INDEX
    Explanations

    indication

    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
     raus
    -0.69
     sem
    -0.69
    imov
    -0.69
    кри
    -0.67
    femin
    -0.66
     measurements
    -0.66
    madan
    -0.66
     prisa
    -0.65
    measurements
    -0.65
     crowned
    -0.64
    POSITIVE LOGITS
    臍
    0.75
     område
    0.71
     الكتاب
    0.69
     پرورش
    0.68
     indications
    0.66
     Riviera
    0.65
     新增
    0.65
    entang
    0.64
     USSR
    0.63
     fortæller
    0.63
    Activations Density 0.043%

    No Known Activations