© 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. 132160
    Prev
    Next
    INDEX
    Explanations

    culture, Liberation Army, bye

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

    negative consequences and systems

    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
    дро
    0.51
    cessor
    0.50
     игровые
    0.48
    皰
    0.47
     médian
    0.46
    イール
    0.46
    顔
    0.45
     LDGs
    0.45
    Се
    0.44
    ваць
    0.44
    POSITIVE LOGITS
    yn
    0.52
    em
    0.51
    interesting
    0.49
    </b>
    0.49
    yr
    0.48
    nab
    0.48
    sk
    0.46
    lib
    0.46
    eps
    0.46
    eso
    0.45
    Activations Density 0.000%

    No Known Activations