© 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. 117881
    Prev
    Next
    INDEX
    Explanations

    statistics of

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

    understanding resistance and facts

    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
    Negative Logits
    يمه
    0.55
    DropDownItems
    0.54
    اني
    0.52
     {{-
    0.52
    ዢ
    0.52
    éntesis
    0.51
    ዦ
    0.51
    كس
    0.50
    كان
    0.50
    보
    0.50
    POSITIVE LOGITS
    ựng
    0.47
    রাও
    0.45
    0.45
     επίσης
    0.44
     kerosene
    0.44
     ST
    0.44
    ”).
    0.44
     spongy
    0.43
     unbalanced
    0.42
    ”.
    0.42
    Activations Density 0.000%

    No Known Activations