© 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. 38258
    Prev
    Next
    INDEX
    Explanations

    driver's Board alternatives level up

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

    rephrasing alternatives

    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
    τζ
    0.53
    ادی
    0.49
    ک
    0.49
    ھر
    0.49
     muri
    0.48
     typing
    0.47
    ڑ
    0.46
    破坏
    0.46
     głównie
    0.46
    ι
    0.46
    POSITIVE LOGITS
    osk
    0.50
     Laufe
    0.50
    ong
    0.46
     Fluss
    0.46
     Dupree
    0.46
     be
    0.46
     أق
    0.46
     ሀ
    0.44
     Pflege
    0.44
    aque
    0.44
    Activations Density 0.000%

    No Known Activations