© 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. 50989
    Prev
    Next
    INDEX
    Explanations

    email not published

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

    suit sensors

    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
    ह
    0.46
    م
    0.45
    query
    0.43
    莧
    0.43
    Format
    0.40
     LDH
    0.40
    니다
    0.40
    o
    0.39
    b
    0.39
    ться
    0.38
    POSITIVE LOGITS
     beserta
    0.48
     পুত্রের
    0.46
     kombin
    0.45
     conco
    0.43
     և
    0.43
     virtu
    0.42
     verpflichtet
    0.41
    និង
    0.41
     sekal
    0.41
     schaffen
    0.40
    Activations Density 0.000%

    No Known Activations