© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99020
    Prev
    Next
    INDEX
    Explanations

    figuring things out or being stuck

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -1.57
    (
    -1.47
    v
    -1.44
     concernés
    -1.38
    >
    -1.36
    l
    -1.33
     –
    -1.31
    d
    -1.30
     beautifully
    -1.27
    =
    -1.27
    POSITIVE LOGITS
     όταν
    1.70
     thofe
    1.67
     with
    1.58
     مكتبه
    1.57
    zzlement
    1.54
    spiller
    1.53
     conector
    1.51
     famosas
    1.50
     thier
    1.49
    בק
    1.48
    Activations Density 0.033%

    No Known Activations