© 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. 22-GEMMASCOPE-RES-131K
    7. 68399
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     makes
    -2.58
     which
    -2.34
     because
    -2.31
     through
    -2.28
     from
    -2.27
     gives
    -2.27
     seems
    -2.27
     became
    -2.27
     although
    -2.23
     when
    -2.20
    POSITIVE LOGITS
    </sup>
    2.44
     NEW
    2.16
    8
    2.16
     wondrous
    2.16
     marvelous
    2.13
     astonishing
    2.11
     bizarre
    2.08
     REALLY
    2.05
     horrifying
    2.05
     flamboyant
    2.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.