© 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. 58848
    Prev
    Next
    INDEX
    Explanations

    independent of

    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
     …
    -1.93
     дают
    -1.93
    …"
    -1.93
     ‘
    -1.86
     Produkten
    -1.84
     

    -1.84
     mangled
    -1.81
    …,
    -1.77
     Verkä
    -1.77
     ’
    -1.67
    POSITIVE LOGITS
    t
    2.16
    ቍ
    2.13
    ت
    2.13
    ୌ
    2.09
     bytu
    2.06
     avto
    1.99
     wykona
    1.97
     milliards
    1.96
    т
    1.93
    𞤢
    1.89
    Activations Density 0.004%

    No Known Activations