© 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. 158885
    Prev
    Next
    INDEX
    Explanations

    annual physical coverage

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

    infrastructure demands

    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
    _
    0.64
    ijo
    0.57
    ong
    0.57
    ul
    0.56
    ᱖
    0.54
    '
    0.54
    de
    0.53
    aw
    0.53
    iko
    0.53
    pe
    0.52
    POSITIVE LOGITS
    牰
    0.48
     variación
    0.45
    售后
    0.45
    सत्ता
    0.44
     областях
    0.44
    сного
    0.44
    ﾀ
    0.44
    仗
    0.42
    딴
    0.42
     OBJECTTYPE
    0.42
    Activations Density 0.000%

    No Known Activations