© 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. 127849
    Prev
    Next
    INDEX
    Explanations

    academic degrees

    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
    餍
    -1.73
    不错
    -1.68
    豨
    -1.62
     bonté
    -1.59
    衚
    -1.57
    𓐍
    -1.55
     когда
    -1.55
    加热
    -1.50
    整个
    -1.48
     déchets
    -1.47
    POSITIVE LOGITS
     to
    1.98
    雳
    1.80
    ان
    1.51
    dasarkan
    1.50
     In
    1.48
    rhosis
    1.48
    tudes
    1.45
    </td>
    1.43
    がいる
    1.41
    ruguay
    1.38
    Activations Density 0.012%

    No Known Activations