© 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. 122104
    Prev
    Next
    INDEX
    Explanations

    rule enforcement and legal applicability

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

    large addressable market

    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
    eld
    0.52
    bibli
    0.52
    politics
    0.49
    \%.
    0.49
    intelligence
    0.47
     полно
    0.47
    phen
    0.46
    АР
    0.46
    ൮
    0.46
    angu
    0.46
    POSITIVE LOGITS
     Class
    0.50
     الحمد
    0.49
     دونك
    0.47
     invol
    0.45
     tree
    0.45
     knuckle
    0.45
     caractère
    0.44
     করিয়াছি
    0.44
     deny
    0.43
     zů
    0.43
    Activations Density 0.000%

    No Known Activations