© 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. 150087
    Prev
    Next
    INDEX
    Explanations

    absolute security

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

    scope and limitations

    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
    h
    0.50
    esen
    0.48
    .
    0.46
    ren
    0.44
    ro
    0.43
    anks
    0.43
    lica
    0.43
     replaced
    0.42
    sen
    0.42
    erst
    0.42
    POSITIVE LOGITS
     እንቅ
    0.56
    supportsFocus
    0.56
     নিঃসন্দে
    0.56
    ಡೆ
    0.52
     საშ
    0.51
    Ⲛ
    0.50
    恹
    0.50
     ημέ
    0.50
     জড়
    0.50
    টাইমস
    0.49
    Activations Density 0.000%

    No Known Activations