© 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. 232405
    Prev
    Next
    INDEX
    Explanations

    certification, cyclist, threatens, sponsor

    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
    irlik
    0.51
    ार्
    0.50
    tier
    0.48
    andled
    0.48
    শব
    0.46
    माला
    0.45
    攬
    0.45
    hsl
    0.45
    هن
    0.45
    های
    0.44
    POSITIVE LOGITS
     flooded
    0.51
     Drought
    0.48
     Міні
    0.46
     書い
    0.46
     خواتین
    0.45
     Ə
    0.44
     가지
    0.44
     rameaux
    0.44
     Jugendlichen
    0.44
    NCE
    0.44
    Activations Density 0.000%

    No Known Activations