© 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. 26727
    Prev
    Next
    INDEX
    Explanations

    minimal amounts or exceptions

    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
    QO
    -0.94
     nek
    -0.90
     chien
    -0.89
     蔬菜
    -0.89
    ilità
    -0.88
     biel
    -0.88
     apartament
    -0.88
    mongo
    -0.88
     pantal
    -0.87
     vinyle
    -0.86
    POSITIVE LOGITS
     slightest
    2.91
     even
    2.44
     any
    2.42
     anything
    1.99
     ANY
    1.98
     ANYTHING
    1.90
    少しでも
    1.82
     cualquier
    1.72
     даже
    1.72
    任何
    1.66
    Activations Density 0.066%

    No Known Activations