© 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. 55657
    Prev
    Next
    INDEX
    Explanations

    can contribute

    np_acts-logits-general · gemini-2.5-flash-lite

    lists, separators, vs

    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
    是一
    0.44
    стром
    0.43
    utenção
    0.43
    لاث
    0.43
    是不
    0.43
     formatos
    0.42
    kut
    0.41
    嘛
    0.41
     सल्
    0.41
    都已经
    0.41
    POSITIVE LOGITS
     Gletscher
    0.55
     Accountants
    0.50
     एग्जाम्स
    0.48
     Gia
    0.46
     McMillan
    0.45
     Bever
    0.45
     Méd
    0.44
     Máy
    0.44
     miso
    0.44
     ナイロン
    0.44
    Activations Density 0.000%

    No Known Activations