© 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. 85572
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     cuando
    -2.16
     to
    -2.09
     when
    -1.91
    </h2>
    -1.88
    ↵
    -1.75
     puede
    -1.71
     that
    -1.70
    </td>
    -1.68
     quando
    -1.66
     podría
    -1.66
    POSITIVE LOGITS
     lavadora
    1.77
    isation
    1.77
    嗐
    1.61
     armadura
    1.59
     estatua
    1.56
     tailles
    1.54
     bouteilles
    1.51
     jaula
    1.50
     península
    1.50
     localización
    1.49
    Activations Density 0.013%

    No Known Activations