© 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. 106816
    Prev
    Next
    INDEX
    Explanations

    of all

    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
     מכל
    -1.97
     EVERYTHING
    -1.94
     لكل
    -1.91
     EVERYONE
    -1.86
    所有的
    -1.85
     לכל
    -1.83
    EVERY
    -1.80
     entire
    -1.78
     모든
    -1.76
    Entire
    -1.73
    POSITIVE LOGITS
     all
    1.12
     NgModule
    0.85
     often
    0.81
     ec
    0.74
     equipo
    0.74
     many
    0.74
    roja
    0.74
    щики
    0.73
     jo
    0.72
     or
    0.71
    Activations Density 0.034%

    No Known Activations