© 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. 2769
    Prev
    Next
    INDEX
    Explanations

    damage the, you why, Nordic states

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

    philosophical to shame and movies

    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
    docs
    0.50
     fruta
    0.47
    *
    0.47
     Mort
    0.46
     hear
    0.45
    cannot
    0.44
     Associations
    0.44
     Hear
    0.43
    ifadə
    0.43
    Replacing
    0.42
    POSITIVE LOGITS
     диамет
    0.54
     탄
    0.48
    zący
    0.46
    識
    0.46
     bloke
    0.46
     ಔ
    0.45
     delving
    0.45
     klasik
    0.44
     blissful
    0.44
     나
    0.44
    Activations Density 0.000%

    No Known Activations