© 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. 4587
    Prev
    Next
    INDEX
    Explanations

    stop, block, hinder

    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
     δεδο
    1.67
    €
    1.52
     хол
    1.38
    вую
    1.37
    setActive
    1.37
    色列
    1.34
    owler
    1.32
    versed
    1.32
    ోంది
    1.31
     cuest
    1.31
    POSITIVE LOGITS
    ㄩ
    1.45
    knit
    1.43
    кс
    1.41
    луч
    1.38
    hi
    1.38
     accessing
    1.38
    말
    1.37
     Combustion
    1.35
    ump
    1.35
    uxe
    1.34
    Activations Density 0.427%

    No Known Activations