© 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. 71849
    Prev
    Next
    INDEX
    Explanations

    largely pretty

    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
     this
    -1.58
     even
    -1.37
     because
    -1.33
     which
    -1.30
     before
    -1.27
     the
    -1.19
     from
    -1.18
     that
    -1.17
     additional
    -1.16
    tså
    -1.15
    POSITIVE LOGITS
     somewhat
    1.78
    slightly
    1.52
     plutôt
    1.50
    Mostly
    1.45
     largely
    1.41
     Slightly
    1.39
     légèrement
    1.36
    somewhat
    1.35
    mostly
    1.35
     marginally
    1.33
    Activations Density 0.061%

    No Known Activations