© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13166
    Prev
    Next
    INDEX
    Explanations

    Theodore Roosevelt, Bunny

    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
     lakini
    -2.63
     logistique
    -2.50
     giacca
    -2.47
    ⾞
    -2.45
    雖然
    -2.45
    кроссовки
    -2.44
    龗
    -2.42
    thanks
    -2.41
    حتى
    -2.41
     felice
    -2.38
    POSITIVE LOGITS
    </h3>
    3.13
    ⟞
    2.88
    </i>
    2.83
    <bos>
    2.52
     Of
    2.41
     Into
    2.38
    荩
    2.36
    玊
    2.34
    
    2.33
    .
    2.30
    Activations Density 0.004%

    No Known Activations