© 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. 40774
    Prev
    Next
    INDEX
    Explanations

    value

    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
     mawar
    -1.27
    した場合
    -1.26
     loca
    -1.22
    後に
    -1.21
     visse
    -1.20
     articol
    -1.19
     pouvant
    -1.18
     Wartawan
    -1.18
    〟
    -1.16
     comprenant
    -1.15
    POSITIVE LOGITS
    <td>
    1.62
     җ
    1.41
    vensko
    1.41
     increíble
    1.37
    蒾
    1.35
    の方も
    1.34
    すら
    1.33
    </em>
    1.33
     even
    1.32
     asomb
    1.30
    Activations Density 0.013%

    No Known Activations