© 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. 26708
    Prev
    Next
    INDEX
    Explanations

    reasoning after why

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

    explaining why and why

    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
    ine
    0.46
    ve
    0.46
    the
    0.45
    tissue
    0.45
     wastage
    0.45
    u
    0.44
    <0xAB>
    0.43
    type
    0.43
    roz
    0.43
    '
    0.43
    POSITIVE LOGITS
     అందుకే
    0.56
     കീഴ
    0.52
     žád
    0.51
    アウトドア
    0.51
     ഉ
    0.50
     ይመ
    0.49
     десятки
    0.49
     גם
    0.49
     Jahrze
    0.49
     ጥሩ
    0.48
    Activations Density 0.036%

    No Known Activations