© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130052
    Prev
    Next
    INDEX
    Explanations

    risk of, the Americans, Lloyd H

    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
     in
    -1.55
     when
    -1.38
     at
    -1.26
     because
    -1.25
     where
    -1.11
     usually
    -1.09
     about
    -1.06
    دهم
    -1.06
     represents
    -1.05
     primarily
    -1.05
    POSITIVE LOGITS
     énorme
    1.44
     versões
    1.23
     réservoir
    1.20
    Liefer
    1.16
     opulent
    1.13
     méda
    1.10
     câble
    1.10
    mortem
    1.09
     extré
    1.08
    Ami
    1.07
    Activations Density 0.000%

    No Known Activations