© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8618
    Prev
    Next
    INDEX
    Explanations

    building abstract concepts

    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_13_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
    er
    2.34
    ⿰
    2.23
    erate
    2.04
    陥
    2.00
    ATE
    1.95
    Headline
    1.91
    Ь
    1.90
    הר
    1.90
     עי
    1.83
    riso
    1.80
    POSITIVE LOGITS
     abe
    2.52
    ရား
    2.42
    瓴
    2.36
    ق
    2.33
    咣
    2.31
    ্পনিক
    2.29
    бин
    2.29
    둑
    2.27
    တည်
    2.25
    塁
    2.25
    Activations Density 0.195%

    No Known Activations