© 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. 112476
    Prev
    Next
    INDEX
    Explanations

    healing response

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

    binomial coefficient

    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
     nejsou
    0.42
    ங்களும்
    0.41
    لان
    0.40
     dijel
    0.39
    桨
    0.39
     بہت
    0.39
     శా
    0.39
     छन्
    0.39
    钢
    0.39
    베
    0.38
    POSITIVE LOGITS
    WIDE
    0.49
    kannya
    0.48
    RTT
    0.47
    ято
    0.46
    óricos
    0.46
     অথ
    0.44
    ENSITY
    0.44
    <0x80>
    0.44
    дали
    0.44
    ENCI
    0.44
    Activations Density 0.001%

    No Known Activations