© 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. 191804
    Prev
    Next
    INDEX
    Explanations

    next installment

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

    AI previous versions convenience extension

    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
    exponential
    0.49
     maggiori
    0.47
    bangan
    0.46
    ^{\
    0.46
    lighter
    0.45
    JL
    0.44
    ponsor
    0.44
    JOY
    0.44
    ↕
    0.44
    nationality
    0.43
    POSITIVE LOGITS
     optimizations
    0.49
     étapes
    0.47
     commemorates
    0.46
     accepté
    0.46
     keeps
    0.46
     implies
    0.44
     multipl
    0.44
     workflows
    0.44
     doesn
    0.44
     skis
    0.44
    Activations Density 0.000%

    No Known Activations