© 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. 5987
    Prev
    Next
    INDEX
    Explanations

    Editing, sex, train, poem

    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
    ეგის
    0.41
    σμ
    0.41
     allgemein
    0.41
    芒果
    0.40
    祎
    0.39
    ທີ່ມີ
    0.39
     sashimi
    0.39
     reassured
    0.39
    书记
    0.38
    InMemory
    0.38
    POSITIVE LOGITS
     ²
    0.41
     overt
    0.41
    amnt
    0.41
    cante
    0.41
     jama
    0.40
    escens
    0.40
     elevating
    0.40
     měla
    0.40
    elae
    0.40
     rt
    0.39
    Activations Density 0.010%

    No Known Activations