© 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. 73296
    Prev
    Next
    INDEX
    Explanations

    comparison operators and ranges

    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
    からね
    -0.98
    Even
    -0.84
    Only
    -0.84
    ộn
    -0.81
    וּ
    -0.79
     etc
    -0.79
     providing
    -0.79
     وغير
    -0.78
    あとは
    -0.74
    ⋈
    -0.74
    POSITIVE LOGITS
    ContextCompat
    0.91
     till
    0.87
    memberOf
    0.82
    inderella
    0.75
    ]$
    0.75
     simplest
    0.74
    "/>
    0.73
    )!=
    0.72
    still
    0.71
     Ausgabe
    0.71
    Activations Density 0.015%

    No Known Activations