© 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. 64241
    Prev
    Next
    INDEX
    Explanations

    code syntax or punctuation

    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
     again
    -1.01
     I
    -0.99
     мені
    -0.95
    another
    -0.91
     my
    -0.89
     снова
    -0.89
     отды
    -0.85
     here
    -0.85
     också
    -0.85
     nästa
    -0.82
    POSITIVE LOGITS
     even
    1.02
     setelah
    1.02
    putstr
    0.99
    WillAppear
    0.97
     although
    0.96
    𝗇
    0.93
     sogar
    0.93
     after
    0.92
    код
    0.92
     seharusnya
    0.91
    Activations Density 0.001%

    No Known Activations