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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67171
    Prev
    Next
    INDEX
    Explanations

    URL paths and script commands

    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_22/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
     alcune
    -1.22
     PETER
    -1.16
     JOHN
    -1.16
    still
    -1.12
     dando
    -1.11
     ۱۱
    -1.10
     Sept
    -1.10
    ruary
    -1.09
     unterschiedlich
    -1.06
     alcuni
    -1.05
    POSITIVE LOGITS
    ético
    1.20
     create
    1.16
     start
    1.13
     weirdly
    1.13
     oddly
    1.13
     started
    1.09
     inspiri
    1.08
    Two
    1.08
     want
    1.07
     Completely
    1.06
    Activations Density 0.004%

    No Known Activations