© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 114291
    Prev
    Next
    INDEX
    Explanations

    foreign language or script

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

    Instagram story viewer

    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
     effettuare
    0.43
     functionalities
    0.42
    ;?>
    0.42
    TTLE
    0.42
     みたい
    0.42
    ooli
    0.42
    াকাছি
    0.41
     ର
    0.41
     multifunctional
    0.41
    াকিস্ত
    0.40
    POSITIVE LOGITS
     Gere
    0.43
    пил
    0.39
    سین
    0.39
    अनु
    0.38
    अग
    0.38
    hide
    0.38
     Alphon
    0.38
    Гор
    0.38
     Sigh
    0.38
    ད་
    0.38
    Activations Density 0.019%

    No Known Activations