© 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. 130520
    Prev
    Next
    INDEX
    Explanations

    changes in

    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
     pattes
    -1.29
     verbind
    -1.27
     dokter
    -1.27
     endroits
    -1.21
     discer
    -1.20
    釓
    -1.20
     ayur
    -1.20
     actuellement
    -1.20
     œufs
    -1.18
     verhind
    -1.17
    POSITIVE LOGITS
     in
    1.81
     on
    1.53
     changes
    1.52
     at
    1.48
     or
    1.45
     their
    1.42
     took
    1.41
     had
    1.33
     three
    1.33
     people
    1.30
    Activations Density 0.134%

    No Known Activations