© 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. 34-GEMMASCOPE-RES-131K
    7. 78151
    Prev
    Next
    INDEX
    Explanations

    order of magnitude or range

    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_34/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
    Gebruik
    -0.82
     exactly
    -0.82
     davvero
    -0.81
    املة
    -0.81
     almost
    -0.79
     户
    -0.78
     ਨੂੰ
    -0.77
    ſen
    -0.77
    jaus
    -0.76
     xuống
    -0.75
    POSITIVE LOGITS
     range
    2.27
     neighborhood
    1.98
     vicinity
    1.84
     region
    1.77
     районе
    1.76
     neighbourhood
    1.71
     ballpark
    1.61
    range
    1.45
    neighborhood
    1.45
     ranges
    1.34
    Activations Density 0.026%

    No Known Activations