© 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. 14850
    Prev
    Next
    INDEX
    Explanations

    much followed by degree or attribute

    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
    
    -2.67
    栳
    -2.61
     successes
    -2.56
    咵
    -2.52
     participado
    -2.52
     easiest
    -2.42
     ネタバレ
    -2.41
    栊
    -2.41
    銠
    -2.31
    휀
    -2.31
    POSITIVE LOGITS
    м
    2.97
     When
    2.84
    AutoresizingMask
    2.81
    '
    2.72
     Our
    2.53
     That
    2.52
     "
    2.41
    which
    2.39
     For
    2.34
    「
    2.34
    Activations Density 0.026%

    No Known Activations