© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2308
    Prev
    Next
    INDEX
    Explanations

    false confirmation validity

    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_13_width_65k_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
     interact
    0.94
     digit
    0.92
     ஃப
    0.91
     guinea
    0.91
     어떤
    0.91
     biennial
    0.90
     answer
    0.88
     투
    0.88
     हफ्ते
    0.88
     அளவுக்கு
    0.88
    POSITIVE LOGITS
    仪式
    1.12
    廟
    1.02
    セレ
    0.97
     Ceremony
    0.95
     reconocimiento
    0.95
     ceremonia
    0.95
     ceremonies
    0.93
     ceremony
    0.91
     reconhecimento
    0.90
    之
    0.90
    Activations Density 0.088%

    No Known Activations