© 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. 27853
    Prev
    Next
    INDEX
    Explanations

    java class names

    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
     inéd
    -1.27
    crème
    -1.25
     célè
    -1.23
    parfum
    -1.23
    ӏ
    -1.22
     pán
    -1.19
     stratég
    -1.18
     flesta
    -1.16
     fût
    -1.14
     więc
    -1.13
    POSITIVE LOGITS
    前半
    1.01
     To
    1.01
     How
    0.95
    C
    0.94
    genheit
    0.90
    nelles
    0.90
    つは
    0.89
     D
    0.88
     P
    0.87
    A
    0.87
    Activations Density 0.007%

    No Known Activations