© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10417
    Prev
    Next
    INDEX
    Explanations

    gold and lion discussions

    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_7_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
    oon
    2.87
    ристи
    2.84
     $\}$
    2.72
    ون
    2.72
    ryst
    2.70
    ide
    2.53
    ృష్
    2.47
    彡
    2.46
     habido
    2.44
    im
    2.43
    POSITIVE LOGITS
    ••••
    2.73
     mere
    2.64
    akey
    2.63
    ANIUM
    2.60
    ્ઞ
    2.59
    сть
    2.54
    isopropyl
    2.46
    
    2.44
    뻐
    2.42
     put
    2.36
    Activations Density 0.002%

    No Known Activations