© 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. 166233
    Prev
    Next
    INDEX
    Explanations

    acupuncture, recipe, professional

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

    claims that arguing that

    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
     recomb
    0.47
     gestion
    0.47
     reen
    0.46
    しかし
    0.44
     persistently
    0.44
    개
    0.44
    ils
    0.43
    INGS
    0.42
     thickly
    0.42
     reconstit
    0.42
    POSITIVE LOGITS
     wcześ
    0.46
     Shayari
    0.46
     الماس
    0.46
    ({},
    0.45
     മുഖ്യമ
    0.45
    ,"@
    0.45
     tayo
    0.44
    lerimiz
    0.43
     、,
    0.43
     Олександр
    0.43
    Activations Density 0.000%

    No Known Activations