© 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. 71844
    Prev
    Next
    INDEX
    Explanations

    together with or

    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
    -2.69
     et
    -2.63
    V
    -2.45
    S
    -2.39
    N
    -2.31
     inverse
    -2.19
    able
    -2.09
     zijn
    -2.02
    K
    -2.00
     ganze
    -1.98
    POSITIVE LOGITS
    棪
    2.78
     Also
    2.52
     Possibly
    2.34
     Relatively
    2.27
     Hinsicht
    2.22
     Mainly
    2.17
     Especially
    2.16
    髕
    2.16
    虽说
    2.16
     Somewhat
    2.14
    Activations Density 0.013%

    No Known Activations