© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141417
    Prev
    Next
    INDEX
    Explanations

    contains information about our / includes / contract

    np_acts-logits-general · gemini-2.5-flash-lite

    & followed by Ref, or, x, Creek, Early, will, team, some, ", Filtering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    =")"
    0.47
    ༦
    0.46
     замеча
    0.45
     собак
    0.45
     খুব
    0.44
     क्र
    0.43
    म्मू
    0.42
    𝘮
    0.42
    [multimodal]
    0.41
     نیاز
    0.41
    POSITIVE LOGITS
     সকলকে
    0.50
    probs
    0.46
     সবাইকে
    0.46
    نان
    0.45
    ultan
    0.45
    ך
    0.45
     Everyone
    0.44
    ’
    0.44
     sorrows
    0.44
     والذي
    0.42
    Activations Density 0.001%

    No Known Activations