© 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. 16-GEMMASCOPE-2-RES-262K
    4. 138105
    Prev
    Next
    INDEX
    Explanations

    marlin and tuna

    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_16_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
    ”.
    0.61
     университета
    0.59
     oyster
    0.58
     እንዲሁም
    0.58
     shellfish
    0.57
     INSEE
    0.56
     బల
    0.55
    “
    0.55
     ہے
    0.55
     ”,
    0.55
    POSITIVE LOGITS
    方法
    0.61
    Т
    0.57
    <0x95>
    0.54
    женности
    0.54
     crédit
    0.53
     surpre
    0.52
    事
    0.52
     gebru
    0.52
    כים
    0.52
     rayos
    0.52
    Activations Density 0.001%

    No Known Activations