© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    booting, async, handling

    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
    تش
    1.11
     Geschenk
    1.11
    PINK
    1.06
    رت
    1.05
    트
    1.04
    狱
    1.04
    乔
    1.04
    同事
    1.02
     ميل
    1.02
     Чи
    1.02
    POSITIVE LOGITS
    colas
    0.89
    oseconds
    0.88
     (…)
    0.84
    ebles
    0.83
    nders
    0.83
     शह
    0.79
    Synopsis
    0.78
    incent
    0.77
    olymer
    0.77
    imers
    0.76
    Activations Density 0.000%

    No Known Activations