© 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. 210027
    Prev
    Next
    INDEX
    Explanations

    coffee shop

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

    shellcode, filters, terminate

    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
    鯢
    0.48
    銘
    0.47
     comrade
    0.47
    Bingo
    0.46
    ಕ್ರ
    0.45
    اہم
    0.45
    billion
    0.45
     Vaccine
    0.44
    おお
    0.43
    Virus
    0.42
    POSITIVE LOGITS
     étapes
    0.46
    堷
    0.44
     झ
    0.43
    取决
    0.43
     იაპ
    0.43
     instagram
    0.41
     atte
    0.41
     этапе
    0.40
    akespeare
    0.40
     gerekir
    0.40
    Activations Density 0.000%

    No Known Activations