© 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. 66098
    Prev
    Next
    INDEX
    Explanations

    variable names and code keywords

    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
     where
    -0.97
     Grüßen
    -0.92
     Vereinig
    -0.90
    These
    -0.89
    ImageButton
    -0.86
     Vorsitzender
    -0.86
     include
    -0.84
     on
    -0.83
     returned
    -0.82
    onnaise
    -0.82
    POSITIVE LOGITS
    ovým
    0.97
    以外にも
    0.94
     semmi
    0.93
    िति
    0.91
     étendue
    0.90
     ganadores
    0.90
    ән
    0.89
    ⌝
    0.89
    要用
    0.88
     Rides
    0.87
    Activations Density 0.006%

    No Known Activations