© 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. 128078
    Prev
    Next
    INDEX
    Explanations

    natural followed by a type

    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
    簠
    -3.44
    馓
    -3.20
    mbgg
    -2.89
    讦
    -2.77
    ৢ
    -2.63
    ཌ
    -2.53
     ron
    -2.53
     .......
    -2.50
     !!!!!
    -2.44
    赑
    -2.44
    POSITIVE LOGITS
    T
    3.17
     epitom
    3.08
     burgeoning
    3.06
    “
    3.05
    Even
    3.03
     allow
    3.00
    鋮
    2.88
     increases
    2.84
     usually
    2.84
    Just
    2.83
    Activations Density 0.017%

    No Known Activations