© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25137
    Prev
    Next
    INDEX
    Explanations

    units of length and energy

    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
    ید
    0.46
    인
    0.45
    ور
    0.43
     tourisme
    0.42
     mundial
    0.41
     CERN
    0.40
    처
    0.40
    મ
    0.40
     Adriatic
    0.39
     Scientist
    0.39
    POSITIVE LOGITS
    痔
    0.48
    ibranch
    0.45
    expressed
    0.45
    ispielsweise
    0.45
     ಮಾತ
    0.45
    ವೂ
    0.45
    cents
    0.43
    ঠাকুর
    0.43
    arnings
    0.43
     аласыз
    0.43
    Activations Density 0.001%

    No Known Activations