© 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. 34-GEMMASCOPE-RES-131K
    7. 32589
    Prev
    Next
    INDEX
    Explanations

    brackets and colons

    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_34/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
    (
    -1.00
    </tr>
    -0.93
    té
    -0.85
    *+
    -0.83
    телем
    -0.83
    を
    -0.80
    ches
    -0.80
     Tradu
    -0.79
    *
    -0.78
     rotu
    -0.77
    POSITIVE LOGITS
    んですね
    1.11
     cubre
    1.04
     costuma
    1.04
    nosotros
    1.01
     invitar
    0.98
    mochila
    0.97
     jednod
    0.94
     Benutzer
    0.94
     llorar
    0.94
    Hauteur
    0.94
    Activations Density 0.059%

    No Known Activations