© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4983
    Prev
    Next
    INDEX
    Explanations

    those followed by a descriptor

    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
    ı
    2.81
    ों
    2.57
    ের
    2.56
     `;
    2.48
    рити
    2.41
    рис
    2.38
    ы
    2.38
    䔀
    2.34
    ésus
    2.31
    ات
    2.31
    POSITIVE LOGITS
    ه
    3.32
    ו
    2.76
    нном
    2.66
    에
    2.61
    i
    2.59
    a
    2.55
    iidae
    2.48
    н
    2.42
    enka
    2.38
    دق
    2.38
    Activations Density 0.075%

    No Known Activations