© 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. 60005
    Prev
    Next
    INDEX
    Explanations

    rescue craft and scientific series

    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
    tą
    -1.84
    ном
    -1.59
    line
    -1.48
     getting
    -1.48
     there
    -1.44
    ious
    -1.39
     epitom
    -1.39
     Apos
    -1.37
     facilitates
    -1.36
     ALWAYS
    -1.36
    POSITIVE LOGITS
     are
    2.42
     were
    1.98
    鮰
    1.66
     to
    1.65
     of
    1.60
    lxt
    1.59
    ⧪
    1.56
    jbl
    1.52
    rset
    1.52
    secutions
    1.49
    Activations Density 0.498%

    No Known Activations