© 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. 176079
    Prev
    Next
    INDEX
    Explanations

    paths, evaluates, sedan

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

    assess the situation

    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
    πε
    0.56
     suunn
    0.54
     posséd
    0.52
    لم
    0.50
    تص
    0.49
     tinggi
    0.47
    鉅
    0.46
     Nights
    0.46
    辗
    0.45
    इसी
    0.44
    POSITIVE LOGITS
     کرتے
    0.47
     doubtless
    0.46
     ఎలాంటి
    0.46
     थोड़ी
    0.45
     作り
    0.45
     INPUT
    0.44
     საჭ
    0.44
     మేరకు
    0.44
     diverge
    0.44
    ដើ
    0.43
    Activations Density 0.001%

    No Known Activations