© 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. 200372
    Prev
    Next
    INDEX
    Explanations

    performance, capabilities, communication

    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
    ነስ
    0.48
    e
    0.46
    다
    0.45
    नए
    0.42
    ამაშ
    0.42
    g
    0.42
    க
    0.41
    Wooden
    0.41
    al
    0.40
    قال
    0.40
    POSITIVE LOGITS
     anderen
    0.48
    其它
    0.48
     長財布
    0.46
     tranquille
    0.46
     corrente
    0.46
     ৪৮
    0.46
     প
    0.44
    ジャケット
    0.44
    IntValue
    0.44
     others
    0.44
    Activations Density 0.003%

    No Known Activations