© 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. 5442
    Prev
    Next
    INDEX
    Explanations

    someone and following context

    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
    eal
    2.30
    lasses
    2.24
    laz
    2.07
    cula
    2.06
    ا
    2.04
    ection
    1.93
    itives
    1.91
    mán
    1.91
    اً
    1.88
    eram
    1.85
    POSITIVE LOGITS
    P
    1.92
    <bos>
    1.85
     P
    1.82
    蒡
    1.80
    с
    1.76
    자
    1.75
    using
    1.74
     s
    1.74
    ํ
    1.70
    profiles
    1.69
    Activations Density 0.064%

    No Known Activations