© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 8886
    Prev
    Next
    INDEX
    Explanations

    mandoline slicer or binoculars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     Règles
    0.65
    けない
    0.62
     Parsing
    0.60
     Default
    0.59
    Comparer
    0.59
     Kontext
    0.59
    ColumnKind
    0.59
    pleClass
    0.59
    เดียวกัน
    0.59
     Regeln
    0.58
    POSITIVE LOGITS
    用于
    0.77
     оборудования
    0.73
     използ
    0.72
     использу
    0.70
    工具
    0.70
    设备
    0.70
     সরঞ্জাম
    0.70
     사용하여
    0.70
    型号
    0.68
    使える
    0.68
    Activations Density 0.012%

    No Known Activations