© 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. 187379
    Prev
    Next
    INDEX
    Explanations

    got a trendhas thehas theuninstall programs

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

    automation and displacement

    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
    b
    0.49
     hebben
    0.44
     TNT
    0.44
     ADN
    0.42
     ²
    0.42
    j
    0.42
     .
    0.41
     jär
    0.41
    0.41
     La
    0.41
    POSITIVE LOGITS
    िफ
    0.53
    ຕົ
    0.50
    िग
    0.49
    िमा
    0.48
    :...
    0.47
    бер
    0.47
    ificial
    0.46
    wanted
    0.46
    𝕘
    0.46
     embod
    0.46
    Activations Density 0.000%

    No Known Activations