© 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. 115923
    Prev
    Next
    INDEX
    Explanations

    installed on

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

    contextual punctuation and specific terms

    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
    SHIP
    0.52
    نګه
    0.51
    ಋ
    0.51
    ڀ
    0.50
    コール
    0.50
     σύν
    0.50
    ္ဂ
    0.48
    インタ
    0.47
    вета
    0.47
     रॉ
    0.47
    POSITIVE LOGITS
    {
    0.50
    of
    0.47
     invis
    0.44
    lerinde
    0.42
     edt
    0.42
     increases
    0.41
    lere
    0.41
    小区
    0.41
     abol
    0.41
    (
    0.40
    Activations Density 0.000%

    No Known Activations