© 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-16K
    7. 637
    Prev
    Next
    INDEX
    Explanations

    documentation formatting

    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_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
    ックス
    1.51
     altres
    1.49
    ánto
    1.45
    Hochspringen
    1.34
    堛
    1.34
    rzym
    1.31
     negó
    1.31
    tsó
    1.28
     trzec
    1.27
    栦
    1.27
    POSITIVE LOGITS
     and
    1.61
     throughout
    1.57
     striving
    1.55
     with
    1.55
     as
    1.55
     that
    1.52
     literally
    1.51
     thoughtfulness
    1.49
     devoid
    1.49
     thoughtful
    1.49
    Activations Density 0.529%

    No Known Activations