© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14096
    Prev
    Next
    INDEX
    Explanations

    gorge national

    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_7_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
    tı
    2.78
     vijj
    2.55
    োগ
    2.44
    رس
    2.44
    ############
    2.42
     свойств
    2.41
    ми
    2.31
     паспорт
    2.29
    مند
    2.28
    вар
    2.27
    POSITIVE LOGITS
    ploidy
    2.10
    zech
    2.05
    ka
    2.04
    zeniem
    2.02
     t
    1.97
    ulah
    1.97
    bere
    1.97
     bere
    1.92
    coin
    1.92
    batt
    1.89
    Activations Density 0.000%

    No Known Activations