© 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. 107241
    Prev
    Next
    INDEX
    Explanations

    long been

    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
     già
    -1.05
     уже
    -0.97
    hability
    -0.96
    opacity
    -0.96
    Already
    -0.94
     sudah
    -0.92
    already
    -0.89
     oeil
    -0.89
    patience
    -0.89
     already
    -0.88
    POSITIVE LOGITS
     been
    3.11
     had
    1.88
     was
    1.79
     بوده
    1.72
     needed
    1.72
     ollut
    1.71
     gewesen
    1.71
     lacked
    1.68
     felt
    1.57
     wanted
    1.47
    Activations Density 0.085%

    No Known Activations