© 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. 449
    Prev
    Next
    INDEX
    Explanations

    debugging code and development

    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
    s
    2.05
     Qaeda
    1.70
    tire
    1.61
    e
    1.58
    eared
    1.55
    ség
    1.54
    ütte
    1.52
    o
    1.50
    sack
    1.50
    wreck
    1.50
    POSITIVE LOGITS
     municipalities
    1.87
    𝕀
    1.85
    getCharAt
    1.82
    classAttribute
    1.75
     showrooms
    1.74
     amenities
    1.73
     bisnis
    1.72
    getSt
    1.71
     স্থাপ
    1.68
     lokale
    1.67
    Activations Density 0.000%

    No Known Activations