© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13252
    Prev
    Next
    INDEX
    Explanations

    Day X: explorations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     공간
    1.38
     기반
    1.37
    怔
    1.34
    <unused2206>
    1.32
     embeddings
    1.27
     정의역
    1.26
     vài
    1.26
     configs
    1.24
     몇
    1.24
     방식
    1.23
    POSITIVE LOGITS
    Q
    0.99
     Sam
    0.98
     U
    0.94
    Re
    0.92
    H
    0.92
    Par
    0.89
    Ra
    0.89
    U
    0.87
     O
    0.87
     H
    0.87
    Activations Density 0.046%

    No Known Activations