© 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. 63842
    Prev
    Next
    INDEX
    Explanations

    expressed sum

    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
    APPLICATIONS
    -0.77
    Ankara
    -0.75
    getEvent
    -0.74
    elektron
    -0.73
    Kontra
    -0.69
    じゃなくて
    -0.69
    Oni
    -0.66
    credential
    -0.65
     credential
    -0.65
    WEBP
    -0.65
    POSITIVE LOGITS
    言葉を
    0.80
    ridas
    0.80
     наблю
    0.74
    Moved
    0.72
     snorted
    0.71
     hundred
    0.71
     arco
    0.71
    metis
    0.71
    ceq
    0.70
    <?>>
    0.69
    Activations Density 0.018%

    No Known Activations