Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 35796
    Prev
    Next
    INDEX
    Explanations

    search terms and filters

    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
     उपाय
    0.43
     urma
    0.43
    ിലെ
    0.42
     favorite
    0.42
    hang
    0.41
    മ
    0.41
    硙
    0.41
     Psychologist
    0.41
    我现在
    0.40
    ิตย์
    0.40
    POSITIVE LOGITS
    [\
    0.43
     Latinoamérica
    0.41
    .\
    0.41
    __).
    0.41
    Remaining
    0.40
    …’
    0.40
     Euchar
    0.40
     సామ
    0.39
    セレ
    0.39
     Hamming
    0.39
    Activations Density 0.001%

    No Known Activations