© 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. 3562
    Prev
    Next
    INDEX
    Explanations

    api version numbers

    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
     BSData
    2.32
    𒅅
    2.22
    𐰣
    2.20
    𐰑
    2.17
    தமான
    2.11
     mọi
    2.11
    𐰽
    2.11
    ഷ്ട്ര
    2.10
    𒋻
    2.07
    𒀜
    2.07
    POSITIVE LOGITS
    il
    1.37
    ric
    1.33
     says
    1.29
    '
    1.24
    omere
    1.22
    rie
    1.21
    ce
    1.18
    ut
    1.16
    se
    1.15
    ia
    1.14
    Activations Density 0.066%

    No Known Activations