© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5044
    Prev
    Next
    INDEX
    Explanations

    code delimiters or function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    akrishnan
    1.30
     COMEN
    1.18
     Artem
    1.14
     metade
    1.13
    一代
    1.12
    协
    1.12
     moitié
    1.11
    Syair
    1.10
    MED
    1.10
    Calculating
    1.09
    POSITIVE LOGITS
    fahr
    2.24
    Veja
    1.93
     firetruck
    1.93
    意义
    1.92
     supervision
    1.86
    dive
    1.86
     sólida
    1.85
    뢰
    1.83
     patrols
    1.83
     увидеть
    1.82
    Activations Density 0.000%

    No Known Activations