© 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. 12480
    Prev
    Next
    INDEX
    Explanations

    machine brick founded sewing Clay Mr pink white

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

    questions about color

    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
    sellers
    0.33
    ↵
    0.30
    ્વાસ
    0.29
     musicians
    0.27
    venida
    0.26
    SELL
    0.26
     obsah
    0.26
     কর্মী
    0.26
     samtid
    0.26
    ↵↵
    0.25
    POSITIVE LOGITS
    𝓑
    0.32
    ᴇ
    0.32
    嘅
    0.31
    astricht
    0.31
     क़
    0.30
     ایک
    0.30
     Hôtel
    0.30
    чиго
    0.29
    <unused2169>
    0.29
    ohid
    0.29
    Activations Density 0.131%

    No Known Activations