© 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. 47018
    Prev
    Next
    INDEX
    Explanations

    the film

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

    comma, sophisticated understanding

    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
    奋
    0.49
    ająca
    0.46
     hiding
    0.46
     clubs
    0.45
     thrones
    0.44
    О
    0.44
     klubu
    0.44
    φ
    0.43
     hides
    0.43
    fär
    0.43
    POSITIVE LOGITS
     এটিকে
    0.51
    Flair
    0.46
     Flair
    0.44
     تنظیم
    0.44
     নির্দেশনা
    0.44
     সাড়ে
    0.44
    ంలో
    0.43
     সেজন্য
    0.42
    इसे
    0.41
    諭
    0.41
    Activations Density 0.000%

    No Known Activations