© 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. 20838
    Prev
    Next
    INDEX
    Explanations

    timestamps and line numbers

    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
     Its
    -1.78
    Its
    -1.70
     its
    -1.53
     is
    -1.52
     can
    -1.45
    никами
    -1.43
    它的
    -1.34
    完成です
    -1.30
    できる
    -1.27
    遑
    -1.25
    POSITIVE LOGITS
     jesteśmy
    1.52
     kogo
    1.50
     ندار
    1.46
    orrho
    1.45
     oseb
    1.44
     ljudi
    1.44
    とりあえず
    1.43
     poleg
    1.42
     {},
    1.42
    ifolium
    1.41
    Activations Density 0.002%

    No Known Activations