© 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. 64010
    Prev
    Next
    INDEX
    Explanations

    serializedVersion: 2

    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
    ㅅ
    -0.79
     Екатери
    -0.77
     suelo
    -0.77
    ㄹ
    -0.75
    хва
    -0.73
     bowed
    -0.72
    ulon
    -0.70
     Hoa
    -0.69
     Ow
    -0.69
     老
    -0.69
    POSITIVE LOGITS
     بالق
    0.82
    patent
    0.82
    Tangent
    0.79
    Grado
    0.77
    kamers
    0.76
    Slo
    0.74
     ControllerBase
    0.74
    ポリ
    0.74
    tangentMode
    0.73
    runken
    0.72
    Activations Density 0.003%

    No Known Activations