© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14470
    Prev
    Next
    INDEX
    Explanations

    (use-modules "what" unk vomiting OLED

    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
    лү
    1.77
    Ну
    1.77
    Մ
    1.71
    ھا
    1.65
    NUMX
    1.59
    illac
    1.59
    伙
    1.56
    Shift
    1.55
    ڡ
    1.54
    𝙉
    1.53
    POSITIVE LOGITS
    uers
    2.21
    outez
    1.89
     aaye
    1.80
    zust
    1.79
    OOSE
    1.78
     quanta
    1.75
    quera
    1.72
    愎
    1.72
     karte
    1.70
     \]
    1.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.