© 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. 117368
    Prev
    Next
    INDEX
    Explanations

    printers, electronic paper, ink, Epstein narratives

    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
     importing
    -0.72
    Sami
    -0.70
    omba
    -0.69
    Foxy
    -0.69
    Cia
    -0.68
     Aachen
    -0.66
    Twitch
    -0.66
     Saúde
    -0.66
    Taman
    -0.66
    ({'
    -0.65
    POSITIVE LOGITS
     Epson
    1.23
     ET
    1.05
     Workforce
    0.86
    Czas
    0.84
     EPS
    0.84
     Mover
    0.83
     Matsumoto
    0.81
    EPS
    0.81
    ET
    0.81
     Saw
    0.80
    Activations Density 0.032%

    No Known Activations