© 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. 40-GEMMASCOPE-2-RES-262K
    7. 16412
    Prev
    Next
    INDEX
    Explanations

    source.unsplash.com

    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_40_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
    ี
    0.41
    anın
    0.39
     zien
    0.38
    Бо
    0.37
    ڃ
    0.37
    ӟ
    0.37
     unmatched
    0.37
    Asian
    0.36
     druż
    0.36
    по
    0.36
    POSITIVE LOGITS
     SOURCE
    0.58
     Source
    0.54
     source
    0.53
    ISource
    0.52
     Quellen
    0.47
     सोर्स
    0.47
    source
    0.46
     源
    0.44
     источники
    0.44
     subjective
    0.43
    Activations Density 0.006%

    No Known Activations