© 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. 50488
    Prev
    Next
    INDEX
    Explanations

    saved by, open house, console computers

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

    possible ways to it

    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
     hâ
    0.52
     perpendicular
    0.52
     confiança
    0.52
     confianza
    0.51
     折
    0.51
     ယ
    0.50
     例如
    0.49
    |$
    0.49
    ীদার
    0.49
     vacances
    0.48
    POSITIVE LOGITS
    You
    0.48
    imbing
    0.45
     resisting
    0.44
    Mor
    0.44
    <0xA0>
    0.43
    باح
    0.43
    荥
    0.43
    免费
    0.43
    After
    0.43
    fah
    0.43
    Activations Density 0.001%

    No Known Activations