© 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. 40-GEMMASCOPE-2-RES-262K
    7. 91
    Prev
    Next
    INDEX
    Explanations

    social dinners

    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_40_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
    膿
    0.42
    手中的
    0.36
    Tempor
    0.35
     Tempor
    0.35
    iklet
    0.35
    Wonder
    0.34
     realizan
    0.34
    ität
    0.33
    Reli
    0.33
    Interior
    0.33
    POSITIVE LOGITS
    🍽
    0.63
     served
    0.59
     eaten
    0.53
    🍴
    0.50
     Served
    0.50
    🥣
    0.50
     break
    0.50
    🍱
    0.49
    কালীন
    0.48
    ពេល
    0.46
    Activations Density 0.013%

    No Known Activations