© 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. 57540
    Prev
    Next
    INDEX
    Explanations

    email subjects and technical files

    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
    nés
    -0.73
    營業時間
    -0.70
     प्रकाश
    -0.69
     ciś
    -0.68
    logram
    -0.68
     sẽ
    -0.67
     rushed
    -0.66
     méri
    -0.66
    ⠑
    -0.65
     worden
    -0.65
    POSITIVE LOGITS
    ält
    0.75
     справ
    0.70
    Agreed
    0.70
    ilda
    0.68
    partitions
    0.65
     Klu
    0.65
    šti
    0.65
    reason
    0.64
     Sébastien
    0.64
    Circles
    0.63
    Activations Density 0.052%

    No Known Activations