© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10684
    Prev
    Next
    INDEX
    Explanations

    predicting next word sequence

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    /
    0.76
     not
    0.67
     employing
    0.64
     niet
    0.64
    (
    0.63
    not
    0.63
    and
    0.63
     direct
    0.62
     running
    0.62
     vs
    0.62
    POSITIVE LOGITS
    atthena
    0.82
     mycursor
    0.79
    ፈላ
    0.76
    avasena
    0.75
     glBindTexture
    0.75
    퐫
    0.74
     Umgebung
    0.74
     बच्‍चे
    0.73
    pyrimidin
    0.71
     Colombeau
    0.71
    Activations Density 0.017%

    No Known Activations