© 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. 10250
    Prev
    Next
    INDEX
    Explanations

    various account options

    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
     also
    -2.70
     where
    -2.13
     it
    -1.98
     When
    -1.84
     Also
    -1.82
     with
    -1.75
     from
    -1.74
     If
    -1.74
     more
    -1.71
     Additionally
    -1.71
    POSITIVE LOGITS
    obviously
    1.88
    ⠀⠀⠀⠀⠀⠀⠀⠀
    1.75
     menyen
    1.75
     verbe
    1.67
     tirs
    1.63
    ⠀⠀⠀⠀
    1.62
     Rabu
    1.59
     pauv
    1.59
     sekunder
    1.59
    FIRST
    1.55
    Activations Density 0.067%

    No Known Activations