© 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. 76746
    Prev
    Next
    INDEX
    Explanations

    call detail recording

    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
     Axios
    -0.71
    pher
    -0.70
    decken
    -0.68
     Brag
    -0.68
    scheduling
    -0.67
     参
    -0.67
    readOnly
    -0.66
     posteriorly
    -0.66
    xam
    -0.66
    র্ব
    -0.66
    POSITIVE LOGITS
     CDR
    1.19
     Accounting
    1.16
     diameter
    1.09
     accounting
    1.09
     charging
    1.09
    CDR
    1.02
    cdr
    1.02
     cdr
    1.00
     radius
    1.00
     wholesale
    0.99
    Activations Density 0.028%

    No Known Activations