© 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. 23061
    Prev
    Next
    INDEX
    Explanations

    notice or license statements

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

    conversation and license

    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
    t
    0.55
    yu
    0.52
    label
    0.48
     Not
    0.46
    u
    0.46
     label
    0.45
    not
    0.45
    yz
    0.45
    čina
    0.44
    h
    0.44
    POSITIVE LOGITS
    豊富
    0.48
    пов
    0.44
     lungo
    0.43
    ڻ
    0.43
     مض
    0.43
    زع
    0.42
     نر
    0.42
    زا
    0.42
     நிறைவே
    0.42
     उल्
    0.41
    Activations Density 0.000%

    No Known Activations