© 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. 14304
    Prev
    Next
    INDEX
    Explanations

    programming and scripting keywords

    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
    talet
    1.56
    고요
    1.45
    ድን
    1.44
    誦
    1.37
     titik
    1.37
     ಗಳ
    1.35
    కొని
    1.34
    穌
    1.34
    ทราบ
    1.30
     Referential
    1.27
    POSITIVE LOGITS
     minions
    1.55
    DEFAULT
    1.46
     военных
    1.44
     Brigade
    1.42
    :)
    1.41
     DRA
    1.41
    prefix
    1.41
     BOR
    1.41
     liberals
    1.40
    ர்களில்
    1.38
    Activations Density 0.000%

    No Known Activations