© 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. 98977
    Prev
    Next
    INDEX
    Explanations

    unfinished, deprecated, code comments, names

    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
    loten
    -1.05
     tē
    -0.84
     that
    -0.84
    нением
    -0.83
    面白い
    -0.81
    bundles
    -0.80
     También
    -0.79
     жур
    -0.78
    ACHED
    -0.78
    ikit
    -0.77
    POSITIVE LOGITS
     seabed
    0.83
    azienda
    0.79
    hira
    0.75
    дио
    0.75
     sectarian
    0.73
    wk
    0.72
     martyrdom
    0.72
     astral
    0.72
    比べると
    0.72
     webshop
    0.71
    Activations Density 0.000%

    No Known Activations