© 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. 34-GEMMASCOPE-RES-131K
    7. 64976
    Prev
    Next
    INDEX
    Explanations

    specific collocations

    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_34/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
     then
    -0.88
    ()):
    -0.86
    ћ
    -0.84
    "):
    -0.82
    "><?
    -0.80
    isNameExpr
    -0.80
    FPGA
    -0.79
    responseCode
    -0.77
    iligt
    -0.77
     dul
    -0.75
    POSITIVE LOGITS
    anglais
    0.89
     disposing
    0.83
    disposing
    0.81
    壱
    0.80
     Palmas
    0.80
    čila
    0.79
    Hilsen
    0.79
    Numéro
    0.75
    渴望
    0.75
    lence
    0.74
    Activations Density 0.001%

    No Known Activations