© 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. 2712
    Prev
    Next
    INDEX
    Explanations

    faint subtle descriptions

    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
     in
    2.14
     is
    2.02
     the
    2.00
     it
    1.87
     was
    1.82
     on
    1.78
     that
    1.76
     will
    1.74
     a
    1.72
     are
    1.70
    POSITIVE LOGITS
    𒈬
    2.38
    𒆪
    2.34
    𒅗
    2.30
    𒀊
    2.27
    𒃻
    2.21
    𒋗
    2.17
    𐰴
    2.16
    𒅎
    2.15
    𐰇
    2.14
    ዻ
    2.12
    Activations Density 0.326%

    No Known Activations