© 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. 22-GEMMASCOPE-RES-131K
    7. 32926
    Prev
    Next
    INDEX
    Explanations

    bill plunged, associate called, letter says

    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_22/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
     December
    -1.02
     this
    -1.00
     böyle
    -0.98
     January
    -0.95
     kaikki
    -0.93
     these
    -0.93
     Finanzierung
    -0.89
     тези
    -0.89
     April
    -0.88
    *}[
    -0.88
    POSITIVE LOGITS
     continues
    1.23
     meantime
    1.20
     continuing
    1.20
     meanwhile
    1.19
     continued
    1.16
    continuing
    1.11
     continue
    1.09
     finished
    1.05
    uminum
    1.00
     still
    0.96
    Activations Density 0.005%

    No Known Activations