© 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. 124635
    Prev
    Next
    INDEX
    Explanations

    specific entities and measurements

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

    often, common, machines

    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
    ېر
    0.51
    س
    0.50
    و
    0.50
     Bamboo
    0.46
    گی
    0.45
    エー
    0.45
    ри
    0.44
    ع
    0.44
    拟
    0.44
     sportswear
    0.43
    POSITIVE LOGITS
    amette
    0.51
    प्टेंबर
    0.47
     температура
    0.46
     करोड़ों
    0.46
     primeros
    0.46
     pés
    0.45
     março
    0.44
     квартиры
    0.44
     温度
    0.43
    ónicos
    0.42
    Activations Density 0.000%

    No Known Activations