© 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. 10-GEMMASCOPE-RES-131K
    7. 67368
    Prev
    Next
    INDEX
    Explanations

    locations and addresses

    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
    𝗼
    -2.03
    ⼿
    -1.75
    𝗺
    -1.75
     السياس
    -1.58
    惬
    -1.55
    性价比
    -1.55
     ordenador
    -1.54
    ּוֹ
    -1.54
     färg
    -1.52
    ardino
    -1.51
    POSITIVE LOGITS
     to
    2.39
     ὅ
    1.49
     our
    1.38
    ENCIÓN
    1.36
     like
    1.36
     دخترانه
    1.31
    skoda
    1.26
     Schuhe
    1.21
     also
    1.19
    asantry
    1.19
    Activations Density 0.573%

    No Known Activations