© 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. 53649
    Prev
    Next
    INDEX
    Explanations

    release of

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

    preposition after verb

    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
    kBtu
    0.45
     enterr
    0.45
    tDBOutput
    0.44
    ښت
    0.44
     Forests
    0.43
     (|
    0.43
     আলোচ
    0.42
     setzen
    0.42
     familiari
    0.42
     setzt
    0.41
    POSITIVE LOGITS
    reise
    0.45
    *****/
    0.43
    宪
    0.42
    绻
    0.42
    三百
    0.41
    丽
    0.41
    随着
    0.41
     මත
    0.40
    心灵
    0.40
     भाग
    0.40
    Activations Density 0.000%

    No Known Activations