© 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. 139789
    Prev
    Next
    INDEX
    Explanations

    am pm

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

    words or phrases about ability

    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
     době
    0.52
    ंपरिक
    0.48
     бібліоте
    0.46
    рующий
    0.45
    ѧ
    0.45
     científico
    0.44
    rüstung
    0.44
     capuche
    0.43
     früh
    0.42
     pilha
    0.42
    POSITIVE LOGITS
    J
    0.47
     democratic
    0.44
    is
    0.42
     ans
    0.42
     thousands
    0.42
     incumbents
    0.42
     incumbent
    0.42
    V
    0.41
     Rankings
    0.41
     and
    0.41
    Activations Density 0.000%

    No Known Activations