© 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. 10-GEMMASCOPE-RES-131K
    7. 70133
    Prev
    Next
    INDEX
    Explanations

    statements of affirmation or description

    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_10/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
     milano
    -1.58
     واقعا
    -1.48
     barcelona
    -1.45
     napoli
    -1.44
     incess
    -1.43
     aquarelle
    -1.43
     maroc
    -1.41
     procra
    -1.39
     londres
    -1.39
     clio
    -1.38
    POSITIVE LOGITS
     take
    1.59
     their
    1.57
     some
    1.50
     they
    1.48
     then
    1.45
     each
    1.38
     when
    1.33
     than
    1.32
    providedIn
    1.30
     people
    1.30
    Activations Density 0.087%

    No Known Activations