© 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. 47926
    Prev
    Next
    INDEX
    Explanations

    unknown world

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

    milestone, trend, moment

    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
     بینک
    0.61
     시간에는
    0.51
     బ్యాంకు
    0.48
     ଆ
    0.47
     బ్యాం
    0.46
     은행
    0.46
    钡
    0.45
     উৎপ
    0.45
    WebContent
    0.45
    辂
    0.44
    POSITIVE LOGITS
     recharge
    0.47
    )
    0.47
     milestone
    0.45
     trend
    0.45
     demolition
    0.45
     Slice
    0.45
    errated
    0.44
     demonstr
    0.44
     slice
    0.44
     demographic
    0.44
    Activations Density 0.000%

    No Known Activations