© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11988
    Prev
    Next
    INDEX
    Explanations

    specific aspect of

    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
    sequent
    1.31
    rd
    1.30
    Rust
    1.23
     Wiring
    1.21
    ᐃ
    1.21
     crayon
    1.20
     daddy
    1.18
    るのは
    1.17
     اجرای
    1.17
     unveiled
    1.16
    POSITIVE LOGITS
    дій
    1.42
     oportun
    1.38
     $*$
    1.36
    ูนย์
    1.35
     korzyst
    1.35
    สัย
    1.30
     często
    1.30
    בוה
    1.29
     tomo
    1.28
     porcent
    1.28
    Activations Density 0.165%

    No Known Activations