© 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. 29023
    Prev
    Next
    INDEX
    Explanations

    suitability and appropriateness

    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
     infolge
    -1.54
     conquistar
    -1.52
     müm
    -1.48
    ampunk
    -1.48
     entspre
    -1.45
     niente
    -1.44
     erheblich
    -1.43
    笵
    -1.38
     Reſ
    -1.37
    encre
    -1.36
    POSITIVE LOGITS
     for
    1.95
     as
    1.60
    Grath
    1.42
     to
    1.38
     in
    1.38
    t
    1.33
    X
    1.32
     and
    1.26
     &
    1.26
     or
    1.23
    Activations Density 0.040%

    No Known Activations