© 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. 32574
    Prev
    Next
    INDEX
    Explanations

    exploring why things happen

    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
    bed
    0.49
    ビジネス
    0.43
     ಆದರೆ
    0.42
    ([^
    0.42
     ক্যামেরা
    0.41
    サリー
    0.41
    freeze
    0.41
    当社
    0.40
     बेड
    0.40
     ples
    0.40
    POSITIVE LOGITS
    勐
    0.42
     entscheid
    0.40
    oud
    0.39
     conductor
    0.38
    امية
    0.38
     aprendiz
    0.37
    ີ້
    0.37
    nání
    0.37
    ɡ
    0.37
    涳
    0.37
    Activations Density 0.002%

    No Known Activations