© 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. 15378
    Prev
    Next
    INDEX
    Explanations

    neck on the line

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

    idiomatic expressions

    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
     😍
    0.36
    😍
    0.36
     Lua
    0.36
    😌
    0.36
     😊
    0.35
     অর্থাৎ
    0.35
     unable
    0.34
     Which
    0.34
    )-\
    0.33
    导入
    0.33
    POSITIVE LOGITS
     proverbial
    0.47
    сово
    0.45
    като
    0.41
     hostages
    0.41
     exorc
    0.40
    氪
    0.39
    パンツ
    0.39
    сион
    0.38
    铐
    0.38
     egregious
    0.37
    Activations Density 0.190%

    No Known Activations