© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48270
    Prev
    Next
    INDEX
    Explanations

    access control lists

    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
    ností
    -1.64
     In
    -1.54
    Surprisingly
    -1.48
    aziland
    -1.45
    %
    -1.45
     unquestionably
    -1.41
     There
    -1.41
     bekämp
    -1.40
     innovative
    -1.38
     Since
    -1.37
    POSITIVE LOGITS
    ING
    1.49
    してない
    1.48
     restante
    1.46
     japonés
    1.45
     THOSE
    1.45
    ਃ
    1.41
    donde
    1.41
    where
    1.41
     น้ำ
    1.38
     prohibiting
    1.38
    Activations Density 0.025%

    No Known Activations