© 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. 28130
    Prev
    Next
    INDEX
    Explanations

    invention, observation, for, most, unbiased, optimal

    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
    hydration
    0.45
    തിരെ
    0.45
     hugged
    0.44
    AxisSize
    0.44
    𝙚
    0.44
    助
    0.44
     офис
    0.43
     सिव
    0.42
     सिद्धार्थ
    0.42
    檚
    0.42
    POSITIVE LOGITS
    lst
    0.49
     recapit
    0.49
     dalamnya
    0.48
     yourselves
    0.47
     secre
    0.47
     recettes
    0.46
    cF
    0.46
     détermine
    0.45
     dunno
    0.45
     ponto
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.