© 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. 14584
    Prev
    Next
    INDEX
    Explanations

    court | security | airships

    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
    fotografie
    -1.77
     imó
    -1.69
    榛
    -1.63
    umpang
    -1.58
     refugiados
    -1.57
     fieles
    -1.56
     heridos
    -1.55
    fotografía
    -1.54
     levier
    -1.54
     perdidos
    -1.53
    POSITIVE LOGITS
     any
    1.87
     That
    1.65
     вони
    1.65
    d
    1.64
    </td>
    1.63
     for
    1.61
     him
    1.60
     виро
    1.55
    :
    1.53
    <td>
    1.51
    Activations Density 0.087%

    No Known Activations