© 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. 234366
    Prev
    Next
    INDEX
    Explanations

    slap knees

    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
    swan
    0.49
     well
    0.48
    demir
    0.46
     a
    0.45
     Esa
    0.45
    se
    0.44
     sell
    0.44
     one
    0.43
     New
    0.43
    dem
    0.43
    POSITIVE LOGITS
    hrung
    0.52
    嬷
    0.50
     ধর্ষণের
    0.49
     [])
    0.49
    спонд
    0.49
    Dieser
    0.48
    ဠ
    0.48
    aitement
    0.48
     কোন্‌
    0.46
     ধর্ষ
    0.46
    Activations Density 0.001%

    No Known Activations