© 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. 77743
    Prev
    Next
    INDEX
    Explanations

    proper nouns, people's 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
     conducteur
    -0.85
     Pfarr
    -0.81
    pretation
    -0.80
     uttering
    -0.77
     frustration
    -0.75
     další
    -0.75
    วย
    -0.74
     ethos
    -0.72
    จุด
    -0.72
    barui
    -0.69
    POSITIVE LOGITS
    아이
    0.81
    TG
    0.77
     furrow
    0.76
     Soria
    0.73
    lm
    0.73
    targeted
    0.73
     Locked
    0.73
    )</
    0.73
     planted
    0.72
    uali
    0.70
    Activations Density 0.042%

    No Known Activations