© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1956
    Prev
    Next
    INDEX
    Explanations

    fashion or code examples

    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_17_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
     Myst
    1.15
     Machu
    1.07
     Karab
    1.07
     Cardinals
    1.06
     Φ
    1.06
     René
    1.05
    梅里
    1.03
    Francisco
    1.03
     Louisville
    1.03
    佘
    1.03
    POSITIVE LOGITS
     Moore
    1.94
    Moore
    1.88
    Mo
    1.70
     Mo
    1.68
     Mob
    1.66
    モー
    1.65
     MOB
    1.64
     Moor
    1.63
     Moran
    1.63
    Mor
    1.61
    Activations Density 1.232%

    No Known Activations