© 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. 2403
    Prev
    Next
    INDEX
    Explanations

    fractions and mathematical expressions

    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
     '/
    -1.16
     `/
    -1.09
     "/
    -1.07
    ("/
    -1.03
    ('/
    -1.00
    '/
    -0.96
     ¾
    -0.90
    frac
    -0.89
    ="/
    -0.87
     /
    -0.84
    POSITIVE LOGITS
     motorsport
    0.71
    וך
    0.71
     Goi
    0.70
    Osi
    0.70
    amint
    0.69
    틱
    0.69
    ZB
    0.68
    ཐ
    0.68
    춧
    0.67
    ҝ
    0.67
    Activations Density 0.039%

    No Known Activations