© 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. 78891
    Prev
    Next
    INDEX
    Explanations

    compared with or to

    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
     utilizes
    -0.90
    淖
    -0.83
     anyways
    -0.77
    Whilst
    -0.75
     whilst
    -0.75
     utilized
    -0.73
     utilize
    -0.72
     utilizing
    -0.70
     résulte
    -0.70
     querem
    -0.69
    POSITIVE LOGITS
    如图
    0.94
     vergangenen
    0.88
     past
    0.85
     fow
    0.83
    消毒
    0.81
     asa
    0.81
     FRE
    0.78
     Lava
    0.78
    eley
    0.77
     écouter
    0.77
    Activations Density 0.088%

    No Known Activations