© 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. 34-GEMMASCOPE-RES-131K
    7. 32115
    Prev
    Next
    INDEX
    Explanations

    mathematical formatting tokens

    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
     äls
    -0.72
    Ҭ
    -0.71
     laik
    -0.71
    畦
    -0.70
    پان
    -0.69
     previous
    -0.68
    $*$
    -0.67
    ností
    -0.67
     estis
    -0.67
     nata
    -0.66
    POSITIVE LOGITS
     représente
    0.85
     prière
    0.84
    0.83
    在外
    0.82
    aguay
    0.82
    array
    0.82
    装置
    0.82
     array
    0.82
     simplifié
    0.80
     Fairview
    0.79
    Activations Density 0.005%

    No Known Activations