© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 541
    Prev
    Next
    INDEX
    Explanations

    programming contexts or syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    0.84
     -
    0.80
     in
    0.75
    ,
    0.70
     '
    0.69
     Z
    0.68
     un
    0.67
     not
    0.66
     W
    0.64
     (
    0.64
    POSITIVE LOGITS
    ::
    1.34
    .??"]
    1.24
    <unused1679>
    1.24
    .*;
    1.23
    ੲ
    1.19
    .??
    1.19
    <unused745>
    1.18
    ::{
    1.17
    𐰢
    1.17
    𐱃
    1.15
    Activations Density 0.435%

    No Known Activations