© 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. 14374
    Prev
    Next
    INDEX
    Explanations

    the effect/system/ideal

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

    blocks, bunch, characters, alert, controlling

    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
    जय
    0.45
    有很多
    0.44
     (
    0.44
     deserves
    0.43
     समीर
    0.43
     Agar
    0.42
    MY
    0.42
    可以使用
    0.42
    atte
    0.42
    amb
    0.41
    POSITIVE LOGITS
     sbParams
    0.50
     draught
    0.50
     rameaux
    0.49
     quieras
    0.48
     انجین
    0.46
     sejam
    0.46
    裳
    0.46
     ব্রিগেড
    0.46
     fontstyle
    0.46
     kojim
    0.45
    Activations Density 0.000%

    No Known Activations