© 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. 10274
    Prev
    Next
    INDEX
    Explanations

    wild animals and ice

    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
    Negative Logits
    ̪
    2.48
    ng
    2.47
    skaya
    2.39
    ll
    2.39
    sten
    2.28
    abbit
    2.28
    lara
    2.27
    ︎
    2.27
    tenance
    2.20
    یسم
    2.20
    POSITIVE LOGITS
    ي
    3.12
    ו
    2.83
    า
    2.81
    يء
    2.65
    ಿ
    2.61
    es
    2.61
    يّ
    2.47
    ра
    2.44
    ી
    2.37
    enio
    2.29
    Activations Density 0.023%

    No Known Activations