© 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. 224688
    Prev
    Next
    INDEX
    Explanations

    domain, permit, KPIs

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

    answers "False" or "OTHERS"

    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
    }
    0.55
    olov
    0.50
    }');
    0.46
    Y
    0.46
    smiley
    0.45
    xty
    0.44
    &&
    0.44
    ulare
    0.44
     santé
    0.44
    mh
    0.43
    POSITIVE LOGITS
    方向に
    0.49
     खास
    0.46
    درا
    0.46
    ன்ஸ்
    0.45
    რება
    0.45
    ॉड
    0.44
    ковать
    0.44
    ای
    0.44
    א
    0.44
    किम
    0.44
    Activations Density 0.001%

    No Known Activations