© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1404
    Prev
    Next
    INDEX
    Explanations

    URLs and website names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
     spectral
    1.01
     за
    0.97
    Spectral
    0.95
     ба
    0.94
     د
    0.94
    ////////////////
    0.94
    这
    0.92
     ف
    0.92
     slices
    0.92
     shards
    0.91
    POSITIVE LOGITS
    nytimes
    1.08
     केली
    1.06
     comunale
    1.00
    jetbrains
    0.97
    ಳೆ
    0.97
     sinners
    0.95
     아멘
    0.94
    ioen
    0.94
    ίος
    0.93
     स्‍
    0.91
    Activations Density 0.077%

    No Known Activations