© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72917
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by actions

    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
     ''.
    -1.13
     anot
    -1.11
     aga
    -1.10
     impecable
    -1.10
    tiere
    -1.07
     renown
    -1.06
     "'"
    -1.05
     previos
    -1.05
     '#'
    -1.05
     '',
    -1.04
    POSITIVE LOGITS
    :
    1.34
     most
    1.31
     OF
    1.26
     a
    1.17
     be
    1.10
     part
    1.09
    umbnail
    1.09
    瘊
    1.08
     márm
    1.08
    aikan
    1.08
    Activations Density 0.028%

    No Known Activations