© 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. 44600
    Prev
    Next
    INDEX
    Explanations

    setting descriptive terms

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

    anonymous or if

    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
     دليل
    0.50
    兴奋
    0.49
     ভাতা
    0.48
     Paryayvachi
    0.48
     RUN
    0.47
     संवेदना
    0.46
     Tasting
    0.45
    𒆤
    0.45
    loo
    0.45
    _|
    0.45
    POSITIVE LOGITS
     styles
    0.50
     items
    0.47
     parameters
    0.46
     style
    0.45
     metric
    0.45
     temperature
    0.44
     track
    0.44
     image
    0.44
     kv
    0.44
     Assumption
    0.44
    Activations Density 0.000%

    No Known Activations