© 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. 85
    Prev
    Next
    INDEX
    Explanations

    economy and impact

    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
     دونك
    1.98
    间的
    1.95
    Skew
    1.93
    льт
    1.90
    ుల
    1.89
    缥
    1.89
    мень
    1.86
    erver
    1.86
    氩
    1.86
     хранения
    1.85
    POSITIVE LOGITS
     mainly
    1.68
     primarily
    1.65
     intensely
    1.65
     ferocious
    1.63
     contentious
    1.60
     somewhat
    1.59
     dangerously
    1.57
     fiercely
    1.57
     chiefly
    1.55
    兒
    1.50
    Activations Density 0.000%

    No Known Activations