© 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. 137456
    Prev
    Next
    INDEX
    Explanations

    reporting or inquiries

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

    code, matrices, Image, gluten

    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
    ol
    0.48
    **:
    0.46
    orn
    0.46
    op
    0.46
    ac
    0.45
    0.44
    oc
    0.43
     Not
    0.43
    ier
    0.43
     Sard
    0.43
    POSITIVE LOGITS
    塭
    0.52
     protestors
    0.51
     জাগ্র
    0.50
     ilgili
    0.50
     ಕಳೆದ
    0.50
    ב
    0.50
    ર્મા
    0.49
    REIB
    0.48
    ত্যার
    0.48
     മേഖ
    0.48
    Activations Density 0.000%

    No Known Activations