© 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. 39376
    Prev
    Next
    INDEX
    Explanations

    use, buy, mean

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

    ranking is hard

    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
    ስቃ
    0.52
    МИ
    0.49
    配信
    0.47
    ಿತ್ತು
    0.46
    Sicilian
    0.46
    權
    0.44
    觎
    0.44
    CONSTRAINT
    0.44
    ORDON
    0.44
    Gior
    0.43
    POSITIVE LOGITS
     work
    0.58
     usamos
    0.53
    0.53
     use
    0.52
     =
    0.51
     você
    0.51
     you
    0.50
     (
    0.50
     Work
    0.49
     Use
    0.49
    Activations Density 0.000%

    No Known Activations