© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10017
    Prev
    Next
    INDEX
    Explanations

    complex questions with nuanced answers

    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_22_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
    anstalt
    0.98
    monotonic
    0.93
     fugit
    0.93
    耗
    0.92
    мости
    0.92
     fondateur
    0.91
    MTAB
    0.91
    ོང་
    0.90
    pesas
    0.90
    adhat
    0.89
    POSITIVE LOGITS
     mâles
    0.95
    Ừ
    0.92
     Rece
    0.91
    ruf
    0.90
     mâle
    0.85
     Elsa
    0.85
     jus
    0.84
     Cheshire
    0.83
     হু
    0.83
     قر
    0.82
    Activations Density 0.000%

    No Known Activations