© 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. 101172
    Prev
    Next
    INDEX
    Explanations

    academic/legal citations

    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
     then
    -1.79
    WAUKEE
    -1.42
    <td>
    -1.27
     berusaha
    -1.25
    𝗸
    -1.23
     ζωή
    -1.19
     who
    -1.17
    charest
    -1.16
    mathrm
    -1.15
    飲食
    -1.14
    POSITIVE LOGITS
    -
    1.87
    Its
    1.37
     its
    1.23
     reconhe
    1.23
    encing
    1.19
    ㎖
    1.18
    IEnumerable
    1.18
    那种
    1.16
    Further
    1.16
    PÁG
    1.15
    Activations Density 0.097%

    No Known Activations