© 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. 27224
    Prev
    Next
    INDEX
    Explanations

    it might

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

    claws and crustaceans

    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
    <unused31>
    0.63
     торговли
    0.54
    𒊩
    0.54
     সংখ্যালঘু
    0.51
     販売
    0.50
    <end_of_turn>
    0.50
    వృద్ధి
    0.50
     அடையாளம்
    0.50
    สัย
    0.49
    ITwitter
    0.49
    POSITIVE LOGITS
    <b>
    0.59
     Georgia
    0.52
    0.52
     go
    0.50
    ation
    0.49
     crammed
    0.48
     break
    0.47
     Clarks
    0.46
     Darby
    0.45
    In
    0.44
    Activations Density 0.000%

    No Known Activations