© 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. 14516
    Prev
    Next
    INDEX
    Explanations

    Contender /escolha / Aufklärung / Esslöffel / Cuchillo

    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
    𒀯
    2.52
     রাদে
    2.50
    𒄖
    2.44
    𒋀
    2.43
    𒁾
    2.42
     ಇಸ್ಕೊ
    2.40
    𒌵
    2.40
    SRPCS
    2.40
    BEDATUM
    2.40
    𒀳
    2.38
    POSITIVE LOGITS
     a
    1.92
     the
    1.65
     is
    1.53
    1
    1.50
     one
    1.46
    2
    1.45
     to
    1.43
     not
    1.42
     The
    1.37
    1.37
    Activations Density 0.015%

    No Known Activations