© 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. 11983
    Prev
    Next
    INDEX
    Explanations

    explaining code comments

    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
    nde
    2.64
    ázky
    2.52
    挎
    2.46
    ipedi
    2.46
    iction
    2.43
    ectoria
    2.42
    idded
    2.41
    URLException
    2.40
     ireo
    2.39
    őd
    2.37
    POSITIVE LOGITS
    u
    2.55
    y
    2.49
    ي
    2.33
    al
    2.23
    iin
    2.12
    ის
    2.09
    i
    2.08
    詈
    2.07
    া
    1.99
    ``
    1.99
    Activations Density 0.100%

    No Known Activations