© 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. 115438
    Prev
    Next
    INDEX
    Explanations

    value of bacon

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

    gay 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
    dept
    0.49
    的选择
    0.48
    dech
    0.47
    潰
    0.46
    需求的
    0.45
    ناول
    0.45
    Flat
    0.45
     выбира
    0.44
     ఆధ్యాత్మిక
    0.44
    的需求
    0.44
    POSITIVE LOGITS
     관
    0.53
     pats
    0.52
     צ
    0.50
     Miz
    0.48
     ב
    0.48
     stares
    0.47
     מ
    0.46
     što
    0.46
     آب
    0.46
     caps
    0.46
    Activations Density 0.000%

    No Known Activations