© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 252
    Prev
    Next
    INDEX
    Explanations

    git-scm.com or billions of years

    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
     và
    1.30
    และ
    1.28
     and
    1.27
     и
    1.26
    and
    1.05
    с
    1.04
     และ
    1.01
    -
    0.95
     tersebut
    0.93
    값
    0.92
    POSITIVE LOGITS
    <unused2066>
    1.54
     whatnot
    1.49
    auml
    1.47
    <unused969>
    1.46
    <unused1711>
    1.46
    <unused1700>
    1.46
    <unused2034>
    1.45
    <unused321>
    1.45
    <unused334>
    1.42
    <unused1766>
    1.40
    Activations Density 0.608%

    No Known Activations