© 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. 64668
    Prev
    Next
    INDEX
    Explanations

    checkbox or checked

    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
     StatelessWidget
    -0.81
    gebra
    -0.78
    encils
    -0.74
     frivol
    -0.73
    <0x95>
    -0.73
    ripsi
    -0.71
    cial
    -0.70
    suya
    -0.69
    stanbul
    -0.69
    matta
    -0.68
    POSITIVE LOGITS
     checkbox
    4.59
    checkbox
    3.69
     checked
    3.56
     checkBox
    3.22
    Checkbox
    3.22
    CheckBox
    3.19
     check
    3.13
     Checkbox
    3.11
    checked
    2.89
    Checked
    2.88
    Activations Density 0.131%

    No Known Activations