© 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. 31643
    Prev
    Next
    INDEX
    Explanations

    after names or locations

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

    growth and repair; simulates speech; imaginary beard; myelin structures

    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
    <0xA0>
    0.47
    qk
    0.45
     الجه
    0.43
    arti
    0.43
    去年
    0.43
    ándo
    0.42
    γκεκρι
    0.41
    даг
    0.41
    ⚈
    0.40
    <0x81>
    0.40
    POSITIVE LOGITS
     independents
    0.49
     membranes
    0.47
     sile
    0.46
     syllables
    0.46
     congruent
    0.44
    あります
    0.44
     untouched
    0.44
     ふ
    0.43
     Oscill
    0.43
     எதுவும்
    0.43
    Activations Density 0.000%

    No Known Activations