© 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. 10563
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     state
    1.48
     verdiği
    1.37
     record
    1.37
     paz
    1.34
     listing
    1.34
    흠
    1.33
     Zuh
    1.32
     quote
    1.32
    >,
    1.29
     seed
    1.28
    POSITIVE LOGITS
    賁
    2.36
    ilayer
    2.25
    ometries
    2.11
    予算
    2.09
    褙
    2.06
    आरआई
    2.06
    oubl
    2.04
    punyai
    2.04
    querda
    2.04
    rii
    2.01
    Activations Density 0.000%

    No Known Activations