© 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. 91633
    Prev
    Next
    INDEX
    Explanations

    requests that

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

    react with

    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
     corretamente
    0.53
     Música
    0.52
     intérpre
    0.48
     assertTrue
    0.48
    一张
    0.48
     头
    0.47
    baixo
    0.47
    ྰ
    0.47
     toString
    0.47
     Ấn
    0.47
    POSITIVE LOGITS
    лм
    0.51
    DC
    0.49
    IGH
    0.47
    ML
    0.46
    ERS
    0.46
    тку
    0.44
    τσ
    0.44
    iled
    0.43
    WM
    0.42
    шк
    0.42
    Activations Density 0.002%

    No Known Activations