© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12147
    Prev
    Next
    INDEX
    Explanations

    social media handles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imidazo
    0.42
    USTOM
    0.42
    ホームページ
    0.40
    젝트
    0.39
    ።
    0.39
    }-$
    0.38
    Benzoimidazole
    0.38
     Entfer
    0.38
    ☛
    0.38
    冚
    0.38
    POSITIVE LOGITS
    Official
    0.54
     official
    0.50
    tweets
    0.49
    _)
    0.48
    official
    0.48
     tweets
    0.47
    ,@
    0.46
     Official
    0.46
     when
    0.44
     @
    0.44
    Activations Density 0.006%

    No Known Activations