© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48854
    Prev
    Next
    INDEX
    Explanations

    of record or choice

    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
    pendenti
    -0.86
    cipais
    -0.84
    chufe
    -0.80
    ordered
    -0.79
     accéder
    -0.73
     Boun
    -0.73
    })$}
    -0.73
    krä
    -0.73
     جراحی
    -0.73
    leute
    -0.71
    POSITIVE LOGITS
     of
    1.89
     record
    1.61
     Of
    1.26
    Of
    1.18
    record
    1.15
     Record
    1.13
    of
    1.11
     OF
    1.03
    Record
    1.01
    RECORD
    0.93
    Activations Density 0.034%

    No Known Activations