© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 241111
    Prev
    Next
    INDEX
    Explanations

    conditions and capabilities

    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
    uğu
    0.46
    ﺭ
    0.45
    telefone
    0.44
     е
    0.43
    reported
    0.43
    ,
    0.43
    рное
    0.42
     thi
    0.42
     negro
    0.41
    ар
    0.41
    POSITIVE LOGITS
     Ablauf
    0.48
     Preparing
    0.45
     ✔
    0.45
     دریافت
    0.45
     BLAST
    0.43
    isbury
    0.43
    ইয়
    0.43
    ຢ
    0.42
     Substances
    0.42
    ExpNow
    0.42
    Activations Density 0.001%

    No Known Activations