© 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. 107893
    Prev
    Next
    INDEX
    Explanations

    universities and polytechnics

    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
     podjela
    -0.77
     кре
    -0.72
    Sklici
    -0.71
    Compassion
    -0.69
    postgres
    -0.68
    ெ
    -0.67
     član
    -0.66
    ->{
    -0.64
    ichester
    -0.64
    acteria
    -0.64
    POSITIVE LOGITS
     lecturers
    0.79
     lecturer
    0.75
     aband
    0.71
    VIR
    0.71
    Lah
    0.70
    وگ
    0.69
     Crowley
    0.68
    DISTRIBUTION
    0.68
    OAuth
    0.68
     لپ
    0.68
    Activations Density 0.034%

    No Known Activations