© 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. 358
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ו
    0.64
     that
    0.63
     and
    0.61
    ع
    0.61
     वालों
    0.58
    r
    0.57
     AND
    0.57
    classes
    0.56
     (>
    0.56
     ([
    0.56
    POSITIVE LOGITS
     través
    0.65
    ğından
    0.63
    ğı
    0.60
    Ş
    0.56
    egir
    0.56
     வகையான
    0.56
    𝘽
    0.55
    ভাবেই
    0.55
    Ç
    0.54
    થમ
    0.54
    Activations Density 1.907%

    No Known Activations