© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44672
    Prev
    Next
    INDEX
    Explanations

    end of sentences

    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
    引用元
    -1.69
    Elaboración
    -1.55
    DESCRIPCIÓN
    -1.53
    Duración
    -1.45
    ㆁ
    -1.44
     черво
    -1.44
    cestry
    -1.44
    CURSO
    -1.43
    Anwendung
    -1.41
    åter
    -1.41
    POSITIVE LOGITS
     was
    1.81
     be
    1.73
     so
    1.69
     '
    1.51
    (
    1.47
     ?
    1.45
     we
    1.45
     must
    1.41
     would
    1.39
    ’
    1.37
    Activations Density 0.095%

    No Known Activations