© 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. 43225
    Prev
    Next
    INDEX
    Explanations

    The Crimes of Grindelwald

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

    factors and considerations

    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
    同樣
    0.46
     ఆధ్యాత్మిక
    0.46
    韓國
    0.45
    stilling
    0.43
    漢
    0.43
    백
    0.42
    혈
    0.42
    不妨
    0.42
    으로써
    0.42
    第一題
    0.42
    POSITIVE LOGITS
     actors
    0.48
     strategist
    0.45
     alliances
    0.44
     Business
    0.44
     no
    0.43
     companies
    0.42
     nered
    0.42
     देयर
    0.41
     firms
    0.41
    ']
    0.41
    Activations Density 0.000%

    No Known Activations