© 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. 51235
    Prev
    Next
    INDEX
    Explanations

    number of times edited

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

    explanatory phrases and measurements

    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
     Speedway
    0.47
     Series
    0.44
     Skating
    0.44
     Spine
    0.44
     Liaison
    0.44
     Corps
    0.43
     (#
    0.43
     Thierry
    0.43
     CCI
    0.43
     Retry
    0.42
    POSITIVE LOGITS
     פור
    0.45
    ﺴ
    0.45
     عوامل
    0.45
     מד
    0.44
    の名
    0.44
     ଗ
    0.43
     ଜ
    0.43
     장
    0.43
    irat
    0.42
     ने
    0.42
    Activations Density 0.000%

    No Known Activations