© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90665
    Prev
    Next
    INDEX
    Explanations

    ASSEMBLIES

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

    based on prompt

    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
    ٠
    0.45
    ivered
    0.39
    uns
    0.37
    inei
    0.37
    一切
    0.37
    нием
    0.36
    ulata
    0.36
    isms
    0.36
     uncontroll
    0.35
    hooks
    0.35
    POSITIVE LOGITS
    เด
    0.46
     ASSEM
    0.45
     เจ
    0.45
     เด
    0.44
     응
    0.44
    াক
    0.43
     Assemblies
    0.42
    erçe
    0.42
     ASSEMBLY
    0.42
    墀
    0.42
    Activations Density 0.000%

    No Known Activations