© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108290
    Prev
    Next
    INDEX
    Explanations

    8 following closing quote

    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
    tely
    -0.90
    gerichts
    -0.90
    ())
    -0.83
    bringer
    -0.82
    Ą
    -0.82
    ürzt
    -0.82
     osv
    -0.81
     diferentes
    -0.81
     godine
    -0.80
    されていました
    -0.80
    POSITIVE LOGITS
    🧧
    0.89
    áciu
    0.89
     kū
    0.84
    ってこと
    0.82
     لحظه
    0.81
    wać
    0.81
    Еще
    0.80
     normalcy
    0.79
    <0xA3>
    0.79
    ">
    0.79
    Activations Density 0.035%

    No Known Activations