© 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. 200523
    Prev
    Next
    INDEX
    Explanations

    doi: followed by alphanumeric strings

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

    scientific papers and URLs

    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
     %,
    0.48
    apak
    0.48
     가서
    0.48
     topics
    0.46
     जनक
    0.45
     escort
    0.45
     熱
    0.45
     अवतार
    0.43
     जिससे
    0.42
     Hundreds
    0.42
    POSITIVE LOGITS
    وري
    0.50
    боро
    0.45
    ملك
    0.45
    alions
    0.45
     Energía
    0.45
    स्ट
    0.45
    ي
    0.44
    تبه
    0.44
    멘
    0.44
    atost
    0.44
    Activations Density 0.001%

    No Known Activations