© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204461
    Prev
    Next
    INDEX
    Explanations

    maple syrup

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

    sexual exploitation themes

    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
    agam
    0.48
     aktuellen
    0.46
    భర
    0.45
    }$&$-
    0.45
    azer
    0.44
     auff
    0.44
    appa
    0.44
    transpose
    0.43
     নির্ধারণ
    0.43
     entferne
    0.43
    POSITIVE LOGITS
     has
    0.47
     Islington
    0.44
     Texts
    0.44
    ...',
    0.44
     Bayesian
    0.43
    JEN
    0.43
    '},
    0.43
     Implications
    0.43
     WERE
    0.43
     CHICAGO
    0.42
    Activations Density 0.000%

    No Known Activations