© 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. 27051
    Prev
    Next
    INDEX
    Explanations

    indicates similarity or correspondence

    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
     mı
    -0.93
     caos
    -0.91
    нс
    -0.89
    lı
    -0.88
     מִ
    -0.86
    asted
    -0.85
    lowed
    -0.85
     cump
    -0.85
    ша
    -0.85
     haya
    -0.83
    POSITIVE LOGITS
     equally
    1.93
     altrett
    1.81
     correspondingly
    1.81
     corresponding
    1.45
     similarly
    1.43
     igualmente
    1.39
     Equally
    1.39
     entspre
    1.23
     entsprechend
    1.23
     entsprechenden
    1.15
    Activations Density 0.132%

    No Known Activations