© 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. 13198
    Prev
    Next
    INDEX
    Explanations

    oral storytelling and traditions

    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
    δια
    2.02
    edt
    1.96
    ありますが
    1.95
    taş
    1.94
    обходимо
    1.84
     đẩy
    1.84
    紝
    1.83
    ("")]
    1.82
    牖
    1.81
    вары
    1.81
    POSITIVE LOGITS
     ter
    1.63
     goods
    1.60
    <bos>
    1.58
     magnum
    1.55
    まと
    1.53
     Ter
    1.49
    osa
    1.49
     weapons
    1.48
    iter
    1.48
     traction
    1.48
    Activations Density 0.053%

    No Known Activations