© 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. 125041
    Prev
    Next
    INDEX
    Explanations

    to the extent permitted

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

    words ending in or following punctuation

    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
     Playoffs
    0.43
     그리고
    0.43
    óz
    0.41
     မိ
    0.41
    并且
    0.40
    omics
    0.40
    훼
    0.39
    ục
    0.39
    nost
    0.39
    lac
    0.39
    POSITIVE LOGITS
     використання
    0.44
    使い方
    0.44
    軽く
    0.43
    下記の
    0.43
     разработ
    0.43
    初心者
    0.43
    ن
    0.42
     penjelasan
    0.42
     sizzling
    0.41
     Gupta
    0.41
    Activations Density 0.001%

    No Known Activations