© 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. 64250
    Prev
    Next
    INDEX
    Explanations

    includes, incorporates, lacing, with

    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
    acier
    -0.85
    Mhz
    -0.82
    ganya
    -0.77
    исленность
    -0.76
    makeatletter
    -0.70
    的问
    -0.70
     либо
    -0.69
    tito
    -0.69
     Ignacio
    -0.68
    𝙆
    -0.68
    POSITIVE LOGITS
     reinforcements
    0.94
     zones
    0.88
     mapped
    0.84
     направлении
    0.82
     anatomical
    0.79
     compatible
    0.78
    dafri
    0.78
     zoning
    0.78
    ພ
    0.77
     tensions
    0.77
    Activations Density 0.021%

    No Known Activations