© 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. 107924
    Prev
    Next
    INDEX
    Explanations

    column sizes xs sm md

    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
     which
    -0.94
     ešte
    -0.90
     tiež
    -0.85
     ambig
    -0.83
    ודש
    -0.81
     and
    -0.81
     開催
    -0.80
    āb
    -0.80
    anske
    -0.79
     piensan
    -0.77
    POSITIVE LOGITS
     md
    1.05
     xs
    0.93
     tablet
    0.88
     sm
    0.88
    LARGE
    0.88
    xs
    0.87
    becomes
    0.84
     essas
    0.83
    teilte
    0.82
    aturas
    0.81
    Activations Density 0.001%

    No Known Activations