© 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. 14858
    Prev
    Next
    INDEX
    Explanations

    news articles URLs

    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
    s
    0.86
    tare
    0.84
    scre
    0.82
    enzione
    0.81
    sail
    0.80
    íduos
    0.80
    tub
    0.80
    aient
    0.79
    tete
    0.78
    sulph
    0.78
    POSITIVE LOGITS
     +(
    0.88
     *(
    0.87
     (?,
    0.78
    자
    0.78
     위의
    0.78
    든지
    0.78
     하나의
    0.78
     둘
    0.77
     겨
    0.76
     연
    0.75
    Activations Density 0.013%

    No Known Activations