© 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. 42809
    Prev
    Next
    INDEX
    Explanations

    actions and tasks performed

    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
     you
    -1.56
     always
    -1.52
     it
    -1.44
     wants
    -1.41
     any
    -1.40
    atedral
    -1.38
     just
    -1.34
     of
    -1.33
     help
    -1.33
     give
    -1.28
    POSITIVE LOGITS
    lization
    1.68
    lizes
    1.66
    lized
    1.48
     instead
    1.35
    lizing
    1.34
    instead
    1.34
     bụ
    1.34
    likely
    1.29
    licopter
    1.27
     ganska
    1.27
    Activations Density 0.127%

    No Known Activations