© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 512
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     genotyping
    1.11
    部件
    1.08
    咖
    1.05
    iation
    1.01
    gathering
    0.96
    웨어
    0.96
    ும்போது
    0.95
    妫
    0.95
     বিএনপির
    0.95
    ेंटिस
    0.94
    POSITIVE LOGITS
    s
    1.23
    ের
    1.22
     až
    1.22
    ycin
    1.20
    sion
    1.19
    ים
    1.13
    いる
    1.13
     exs
    1.12
    ことが多い
    1.12
     asphy
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.