© 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. 11329
    Prev
    Next
    INDEX
    Explanations

    As evolved, beginner, played

    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
    É
    1.57
    La
    1.52
    תיים
    1.46
    Bois
    1.44
    เสื้อ
    1.42
    Equ
    1.42
    THR
    1.41
    cker
    1.41
    Too
    1.41
    喱
    1.40
    POSITIVE LOGITS
    y
    2.33
    عال
    1.98
    gning
    1.96
    ו
    1.95
    此之外
    1.84
    ために
    1.77
    場合
    1.76
    enek
    1.75
    iin
    1.74
    yh
    1.73
    Activations Density 0.000%

    No Known Activations