© 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. 224612
    Prev
    Next
    INDEX
    Explanations

    place names and separators

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

    told to, confidently ferment, highly unlikely

    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
    ));
    0.52
    نج
    0.50
    دأ
    0.50
    ').
    0.48
    »)
    0.47
     تصور
    0.46
    вний
    0.46
     Proposals
    0.46
    )<\
    0.45
    动画
    0.45
    POSITIVE LOGITS
     liquefied
    0.48
     convent
    0.47
     quasip
    0.47
    They
    0.47
     euro
    0.47
     irrever
    0.46
     wouldn
    0.46
     judicial
    0.46
     утром
    0.46
     cob
    0.45
    Activations Density 0.000%

    No Known Activations