© 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. 233346
    Prev
    Next
    INDEX
    Explanations

    healthy andstill atwave ofboosts shine

    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
    <0x0D>
    0.57
    RetValue
    0.51
    PDA
    0.48
     CHEMISTRY
    0.47
    WD
    0.45
     Chemistry
    0.44
    스타
    0.44
     Microsoft
    0.43
    ور
    0.43
     Fertilizer
    0.43
    POSITIVE LOGITS
     그러
    0.49
     केवळ
    0.45
     chants
    0.44
    琕
    0.44
     съем
    0.44
    aulay
    0.44
    ao
    0.44
     පේශ
    0.44
     auffi
    0.44
    eem
    0.43
    Activations Density 0.000%

    No Known Activations