© 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. 74937
    Prev
    Next
    INDEX
    Explanations

    assessing validity

    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
     llegan
    -1.73
    跸
    -1.69
    enderal
    -1.69
    翃
    -1.67
    Ndr
    -1.62
     filozof
    -1.62
    爌
    -1.62
    zmm
    -1.59
     tranſ
    -1.59
     dicen
    -1.55
    POSITIVE LOGITS
    To
    1.89
    For
    1.81
    Being
    1.80
     &
    1.70
    While
    1.53
    From
    1.52
    Having
    1.52
    A
    1.51
     \
    1.48
    Despite
    1.47
    Activations Density 0.068%

    No Known Activations