© 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. 10-GEMMASCOPE-RES-131K
    7. 74817
    Prev
    Next
    INDEX
    Explanations

    numbers after commas or 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_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
     récla
    -1.84
     Temperatura
    -1.74
     Potencia
    -1.66
     souhait
    -1.64
     språk
    -1.61
     Fácil
    -1.61
     plástica
    -1.61
     Especific
    -1.60
     dénon
    -1.60
     hidráulica
    -1.59
    POSITIVE LOGITS
     and
    1.97
     only
    1.60
     from
    1.49
     the
    1.49
     /
    1.30
    versaire
    1.27
    forKey
    1.23
     dónde
    1.22
     where
    1.21
    </em>
    1.20
    Activations Density 0.016%

    No Known Activations