© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41876
    Prev
    Next
    INDEX
    Explanations

    online forums

    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
    焄
    -2.56
    brakk
    -2.47
    y
    -2.38
    驺
    -2.33
     всѣ
    -2.33
     was
    -2.33
    雠
    -2.19
    譟
    -2.17
    אתה
    -2.16
    fører
    -2.16
    POSITIVE LOGITS
    獁
    2.31
    ↵↵
    2.30
    </u>
    2.13
    I
    2.08
    <i>
    2.02
    We
    2.00
     культура
    2.00
    –
    1.99
    <td>
    1.95
    蟶
    1.87
    Activations Density 0.001%

    No Known Activations