© 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. 25251
    Prev
    Next
    INDEX
    Explanations

    currency and technical data markers

    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
     (
    -1.26
     that
    -1.20
     from
    -1.10
     conç
    -1.09
    }}%
    -1.08
     behöver
    -1.06
     by
    -1.05
    Ő
    -1.05
    ∎
    -1.02
    commod
    -1.02
    POSITIVE LOGITS
     alcune
    1.30
     sommige
    1.24
     alcuni
    1.22
     groots
    1.16
     actuels
    1.13
     hvilke
    1.07
    2
    1.07
     buurt
    1.07
     blurb
    1.06
     diabo
    1.02
    Activations Density 0.081%

    No Known Activations