© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 220067
    Prev
    Next
    INDEX
    Explanations

    ornaments and prices

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

    not comfortable doing

    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
     Father
    0.46
     Vacation
    0.46
     პირადი
    0.45
     COMPUTER
    0.44
     Wanneer
    0.44
     Privacy
    0.43
     [](
    0.43
     Ω
    0.43
     Confidential
    0.42
     Quindi
    0.42
    POSITIVE LOGITS
    connectivity
    0.54
    డీ
    0.48
    cross
    0.48
    تنا
    0.47
    يكا
    0.47
    immers
    0.45
    läss
    0.45
    sold
    0.45
    inducing
    0.45
    ździe
    0.44
    Activations Density 0.000%

    No Known Activations