© 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. 4338
    Prev
    Next
    INDEX
    Explanations

    identifying or describing entities

    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
    ی
    3.34
    y
    2.74
    𝗺
    2.49
    s
    2.48
    یوں
    2.37
    '"
    2.31
    kannya
    2.24
    yar
    2.22
    sman
    2.19
    ourke
    2.19
    POSITIVE LOGITS
    ખા
    2.73
    ForItem
    2.58
    estial
    2.53
    र
    2.37
    レクト
    2.32
    缚
    2.30
    嘩
    2.29
    ্লা
    2.26
    פקי
    2.26
    狀
    2.25
    Activations Density 0.768%

    No Known Activations