© 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. 26953
    Prev
    Next
    INDEX
    Explanations

    recommendations and evaluations

    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
     during
    -1.87
     two
    -1.77
     when
    -1.75
     it
    -1.75
     activities
    -1.57
     actions
    -1.54
     almost
    -1.49
     often
    -1.47
     after
    -1.46
     both
    -1.45
    POSITIVE LOGITS
     superbes
    1.50
     biedt
    1.45
     offrant
    1.37
     magnifiques
    1.37
     you
    1.37
     formid
    1.36
     critères
    1.32
     fournisseurs
    1.32
     vaisseaux
    1.31
     klinik
    1.30
    Activations Density 0.022%

    No Known Activations