© 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. 194617
    Prev
    Next
    INDEX
    Explanations

    execution through, impact on, importance of

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

    appears to be

    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
     surgeons
    0.51
    गर्भ
    0.50
    o
    0.49
    гка
    0.47
     dentists
    0.47
     Gosudarstvennyj
    0.45
     Mehr
    0.44
     зміни
    0.44
     Bharatiya
    0.43
     attorney
    0.43
    POSITIVE LOGITS
    דות
    0.50
    測試
    0.46
     appara
    0.46
    ປັນ
    0.45
     μά
    0.44
     സമര
    0.44
    𝙫
    0.43
    ké
    0.43
    OCATION
    0.42
     batalla
    0.41
    Activations Density 0.000%

    No Known Activations