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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56514
    Prev
    Next
    INDEX
    Explanations

    return value or space

    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_65k_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
    ifer
    0.50
    𝟖
    0.48
     બાદ
    0.47
    inhas
    0.47
    ko
    0.46
     parfait
    0.46
     परफेक्ट
    0.44
     balsamic
    0.44
    tono
    0.43
     puja
    0.43
    POSITIVE LOGITS
    ؤول
    0.45
    $)$.
    0.45
     explosive
    0.44
    лот
    0.43
    {\'
    0.43
    连接
    0.42
    ীবন
    0.42
    Measurement
    0.42
     plomb
    0.41
     vivent
    0.41
    Activations Density 0.002%

    No Known Activations