© 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. 102501
    Prev
    Next
    INDEX
    Explanations

    help you achieve

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

    understand questions or confirmations

    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
    値段
    0.50
    ando
    0.46
    os
    0.45
    み
    0.45
    ,
    0.44
    มัน
    0.44
     Tetapi
    0.44
     ridiculously
    0.44
    ::
    0.42
    bon
    0.42
    POSITIVE LOGITS
     prostředí
    0.46
    زى
    0.44
     besitzt
    0.43
     piernas
    0.42
     seiner
    0.42
     confond
    0.42
     überras
    0.41
     pierre
    0.41
    他和
    0.41
    GEBURTSDATUM
    0.41
    Activations Density 0.001%

    No Known Activations