© 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. 12683
    Prev
    Next
    INDEX
    Explanations

    smile widened, goal, theme, snarled

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Outreach
    1.53
     Ν
    1.45
     χ
    1.45
     tumultuous
    1.44
     battles
    1.42
     lifetimes
    1.41
     ἐν
    1.40
    ⓗ
    1.40
    ponsored
    1.39
     outreach
    1.39
    POSITIVE LOGITS
    adikan
    1.27
     bisa
    1.21
    atkan
    1.19
     ternyata
    1.19
    ઓના
    1.17
    ỉ
    1.16
     diberikan
    1.14
     selalu
    1.13
     beberapa
    1.13
    ダ
    1.12
    Activations Density 0.020%

    No Known Activations