© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94198
    Prev
    Next
    INDEX
    Explanations

    examples and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     계속
    0.45
    ｂ
    0.45
     Caramel
    0.44
    に変
    0.43
     subscribe
    0.43
    idunt
    0.43
     responsiveness
    0.42
     drains
    0.41
     communicates
    0.41
     Catar
    0.40
    POSITIVE LOGITS
    ونية
    0.54
    <0x0D>
    0.53
     péld
    0.53
    oszt
    0.49
     örnek
    0.48
    iest
    0.47
    畿
    0.47
    ová
    0.47
     zwe
    0.47
     iure
    0.46
    Activations Density 0.001%

    No Known Activations