© 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-262K
    7. 139039
    Prev
    Next
    INDEX
    Explanations

    continuous learning

    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
    of
    0.68
    א
    0.57
    $
    0.52
    app
    0.49
    Если
    0.49
    ב
    0.48
    el
    0.46
     Revue
    0.46
    ный
    0.45
    Ha
    0.45
    POSITIVE LOGITS
     जो
    0.50
    Methylsulfanyl
    0.46
     dimethyl
    0.46
     behov
    0.46
     മുഖ
    0.45
     Rajiv
    0.44
     જે
    0.43
     അന്ത
    0.43
    🕙
    0.43
    需求的
    0.43
    Activations Density 0.000%

    No Known Activations