© 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. 10462
    Prev
    Next
    INDEX
    Explanations

    proto- words and русский

    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
    ਤਾ
    3.12
    mente
    2.50
    맡
    2.43
    얼
    2.29
    ازت
    2.28
     (’
    2.25
    靂
    2.24
    tdown
    2.19
    
    2.17
    ծ
    2.13
    POSITIVE LOGITS
    a
    2.73
     sliders
    2.66
     snakes
    2.63
    e
    2.60
    vnd
    2.58
     chloro
    2.57
     durs
    2.55
    arid
    2.54
    esque
    2.53
     sparsebundle
    2.51
    Activations Density 0.000%

    No Known Activations