© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67201
    Prev
    Next
    INDEX
    Explanations

    firearms, guns, weapons

    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_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
    $
    -1.51
    ჻
    -1.41
     were
    -1.37
    so
    -1.34
    that
    -1.30
    人が
    -1.25
    dropIfExists
    -1.21
     feiner
    -1.21
    six
    -1.20
    开始了
    -1.20
    POSITIVE LOGITS
    tividade
    1.28
    ㌘
    1.27
    licación
    1.26
    Люби
    1.23
    ?
    1.22
     uses
    1.22
    сії
    1.19
    ėj
    1.18
     has
    1.16
    yasi
    1.16
    Activations Density 0.016%

    No Known Activations