© 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. 30757
    Prev
    Next
    INDEX
    Explanations

    URL query parameters

    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
     whiteColor
    -0.84
     punctu
    -0.82
     óleo
    -0.80
     algemeen
    -0.79
    äler
    -0.78
     circu
    -0.78
    dream
    -0.77
    엌
    -0.76
     zulassen
    -0.75
     debería
    -0.75
    POSITIVE LOGITS
     action
    1.20
    \&
    1.04
     \&
    1.03
     from
    1.02
    action
    1.00
     page
    0.99
     which
    0.99
     op
    0.96
    &__
    0.94
    ulaire
    0.94
    Activations Density 0.021%

    No Known Activations