© 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. 188588
    Prev
    Next
    INDEX
    Explanations

    domains, healthier eating

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

    JOIN, healthy, math environments

    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
    retrofit
    0.46
    ultan
    0.44
     ماما
    0.43
    anyo
    0.42
    accordion
    0.42
     بب
    0.42
    ܪ
    0.42
    市值
    0.41
     گار
    0.40
    each
    0.40
    POSITIVE LOGITS
     itse
    0.47
     driv
    0.46
     ngừng
    0.46
     sám
    0.45
     అనుమ
    0.45
     appunto
    0.45
    貨
    0.45
     unver
    0.44
    某些
    0.44
     Callback
    0.43
    Activations Density 0.001%

    No Known Activations