© 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. 206781
    Prev
    Next
    INDEX
    Explanations

    week, journal, select, Truman

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

    gym memberships

    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
    ㄟ
    0.48
    ěné
    0.47
     WSL
    0.44
    抨
    0.44
     चलते
    0.42
     intercambio
    0.42
     तत्कालीन
    0.42
     récemment
    0.42
    getRequest
    0.41
    getAction
    0.41
    POSITIVE LOGITS
    nimmt
    0.48
    ܡܪ
    0.44
    펩
    0.43
     lands
    0.42
    އް
    0.42
    るのは
    0.42
     esters
    0.41
    གྲ
    0.41
    כ
    0.41
    ებულია
    0.40
    Activations Density 0.000%

    No Known Activations