© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84687
    Prev
    Next
    INDEX
    Explanations

    Lars, Larson, PSC, COMMISSION

    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
     télévis
    -2.72
    
    -2.64
    闳
    -2.56
    
    -2.53
    瑧
    -2.44
    》。
    -2.42
    ⬐
    -2.41
     bahwa
    -2.38
    》（
    -2.34
    戩
    -2.34
    POSITIVE LOGITS
    </h3>
    3.22
    U
    3.19
    D
    2.92
    of
    2.84
    R
    2.81
    </strong>
    2.80
    -
    2.80
    J
    2.77
    e
    2.77
    ⭓
    2.75
    Activations Density 0.004%

    No Known Activations