© 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. 61730
    Prev
    Next
    INDEX
    Explanations

    measurements, numbers, and dimensions

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

    direct manager, teen magazine, NBA

    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
     launcher
    0.44
     enabled
    0.44
     peel
    0.43
     আমাদের
    0.43
    йом
    0.42
     giveaway
    0.42
    …
    0.42
     helped
    0.42
     reimag
    0.41
    ⁺
    0.41
    POSITIVE LOGITS
     세율
    0.52
     சரா
    0.52
    ższ
    0.51
     குறை
    0.47
     arreglo
    0.47
     औसत
    0.47
     увеличить
    0.46
     faiblement
    0.46
     প্রাধান্য
    0.45
     സ്ത്രീ
    0.44
    Activations Density 0.000%

    No Known Activations