© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 97
    Prev
    Next
    INDEX
    Explanations

    all, every, each, everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    B
    1.32
    G
    1.28
     Some
    1.23
     Only
    1.22
    F
    1.20
    S
    1.17
     Many
    1.13
    Y
    1.12
    D
    1.12
    T
    1.11
    POSITIVE LOGITS
     imaginable
    1.36
     conceivable
    1.35
     else
    1.34
    حول
    1.30
    <unused1877>
    1.29
    Bibitem
    1.28
    wheres
    1.28
     einzelnen
    1.25
     demás
    1.23
    ឡិចត្រូ
    1.22
    Activations Density 0.719%

    No Known Activations