© 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. 150587
    Prev
    Next
    INDEX
    Explanations

    by a

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

    verbal, environment, available, relevant, percentage

    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
    Center
    0.43
     脚
    0.42
     চিন
    0.41
     எடை
    0.41
    স্তের
    0.40
     Bolívar
    0.40
    Carl
    0.39
    Corner
    0.39
    苇
    0.39
    ienti
    0.38
    POSITIVE LOGITS
    可能會
    0.50
    itals
    0.46
     verhindert
    0.44
    ਰ
    0.44
    ائيل
    0.44
    टरनेट
    0.44
    лох
    0.44
     unabhäng
    0.43
    razol
    0.43
    ഡ്
    0.43
    Activations Density 0.000%

    No Known Activations