© 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. 78941
    Prev
    Next
    INDEX
    Explanations

    book citations and titles

    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
     some
    -0.91
     although
    -0.88
     even
    -0.88
     like
    -0.85
     on
    -0.82
     for
    -0.79
     because
    -0.77
    dington
    -0.77
     three
    -0.77
     several
    -0.77
    POSITIVE LOGITS
     Accessed
    1.27
    appé
    0.88
    ficulties
    0.87
     Edited
    0.87
    ælde
    0.82
    modellen
    0.82
    beispiel
    0.82
     gegenüber
    0.81
     https
    0.81
    hiel
    0.81
    Activations Density 0.003%

    No Known Activations