© 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. 10669
    Prev
    Next
    INDEX
    Explanations

    pinning, identifying, or pegging

    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
    ↵↵
    -2.36
    .
    -2.03
     humeur
    -1.99
    (
    -1.99
    }
    -1.84
    骓
    -1.71
    \}
    -1.70
     humide
    -1.69
     autonomie
    -1.68
    ☑️
    -1.67
    POSITIVE LOGITS
    </strong>
    2.23
    ⢎
    2.09
    漚
    2.09
    那时
    1.96
    ashqai
    1.95
    of
    1.95
    *,
    1.88
    recette
    1.88
     stück
    1.84
    著名的
    1.83
    Activations Density 0.005%

    No Known Activations