© 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. 2358
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    ギター
    0.38
    ︽
    0.37
    頬
    0.37
    <unused72>
    0.36
    പോലെ
    0.35
    miktar
    0.35
    馋
    0.35
    ابان
    0.35
     मोटरसा
    0.35
    щих
    0.35
    POSITIVE LOGITS
    5
    0.59
    0
    0.50
    6
    0.47
    4
    0.46
    7
    0.46
     million
    0.43
     liters
    0.43
     kg
    0.43
    ↵
    0.43
    it
    0.42
    Activations Density 0.082%

    No Known Activations