© 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. 2949
    Prev
    Next
    INDEX
    Explanations

    https://

    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
    ВД
    2.67
    팅
    2.56
    em
    2.52
    N
    2.44
     ch
    2.39
    convertTo
    2.35
    कारात्मक
    2.31
    rootDir
    2.29
    "})
    2.27
    ",
    2.23
    POSITIVE LOGITS
    ScriptAssemblies
    3.24
    ographystyle
    3.11
     кушымта
    2.96
     bith
    2.91
    স্পতি
    2.91
    गुज
    2.88
    驒
    2.88
    ᱽ
    2.83
    tug
    2.83
    يي
    2.82
    Activations Density 0.046%

    No Known Activations