© 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. 89480
    Prev
    Next
    INDEX
    Explanations

    grams and protein

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

    programming keywords and sequences

    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
    秇
    0.31
    edk
    0.28
    đồng
    0.27
    amending
    0.27
    strtolower
    0.27
    하니
    0.26
     SCIENCES
    0.26
    嬂
    0.26
     এমন
    0.25
    avaju
    0.25
    POSITIVE LOGITS
     klas
    0.28
    بيك
    0.28
     de
    0.27
    ژ
    0.27
     Heartland
    0.27
     of
    0.26
     Pompe
    0.26
    ّ
    0.26
     Breakthrough
    0.26
     />
    0.26
    Activations Density 0.001%

    No Known Activations