© 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. 7065
    Prev
    Next
    INDEX
    Explanations

    not only

    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
     actually
    -1.38
     légère
    -1.15
     italienne
    -1.13
     while
    -1.13
    ste
    -1.09
     couverte
    -1.09
    istive
    -1.08
     /\
    -1.06
    }`);
    -1.05
     МИ
    -1.04
    POSITIVE LOGITS
     but
    1.52
     však
    1.41
     his
    1.35
     Rè
    1.29
     irgendwann
    1.20
     mittlerweile
    1.16
     Рекоменду
    1.16
     ohnehin
    1.16
     milieux
    1.16
     polem
    1.16
    Activations Density 0.060%

    No Known Activations