© 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. 31766
    Prev
    Next
    INDEX
    Explanations

    image shields and random number generation

    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
     ejercicios
    -0.81
     sjuk
    -0.81
     Hammers
    -0.80
     lít
    -0.76
     Booker
    -0.75
     Weich
    -0.75
    Summer
    -0.75
     Shadow
    -0.73
    miami
    -0.73
     enfermos
    -0.72
    POSITIVE LOGITS
    nextInt
    0.68
    rigal
    0.68
     passat
    0.66
     though
    0.65
     battled
    0.64
     ROLL
    0.64
     בישראל
    0.63
     Gestão
    0.62
     ROUT
    0.62
     cafés
    0.61
    Activations Density 0.070%

    No Known Activations