© 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. 239682
    Prev
    Next
    INDEX
    Explanations

    killing orthat masquerade

    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
    我现在
    0.51
    ᆨ
    0.49
    ני
    0.48
    💸
    0.48
    ବା
    0.47
    ைகளை
    0.46
    나는
    0.46
    aking
    0.45
    Rise
    0.45
     ሂ
    0.45
    POSITIVE LOGITS
     denominado
    0.48
     Bermuda
    0.47
     lediglich
    0.46
     trivial
    0.46
     Qualifier
    0.45
     decidedly
    0.44
     இடம்பெ
    0.44
     veya
    0.43
     eminently
    0.43
     masking
    0.43
    Activations Density 0.001%

    No Known Activations