© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 248004
    Prev
    Next
    INDEX
    Explanations

    email address, Robin says, Google Analytics, accurate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     दैन
    0.52
     déput
    0.50
     वंचित
    0.48
     percaya
    0.48
     héros
    0.47
     lancement
    0.46
    կ
    0.46
     giỏi
    0.46
     वर
    0.46
    igious
    0.45
    POSITIVE LOGITS
    领
    0.54
     Decoder
    0.50
    预
    0.48
     to
    0.46
    రువు
    0.46
    常用
    0.46
    周边
    0.45
    统
    0.45
    留下
    0.45
    ຫ
    0.45
    Activations Density 0.003%

    No Known Activations