© 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. 197
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
    Assemblée
    1.04
    É
    1.04
    baixo
    1.03
    בודה
    1.02
     odpově
    1.02
    ⁡</
    0.98
    サン
    0.98
    (\{
    0.97
    ディション
    0.96
    ೪
    0.96
    POSITIVE LOGITS
     seems
    1.00
    ,
    1.00
     malad
    0.99
     troubling
    0.98
     enhances
    0.98
     inhibits
    0.96
     diminishes
    0.95
     detrimental
    0.94
     subtle
    0.93
     insidious
    0.92
    Activations Density 7.785%

    No Known Activations