© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2355
    Prev
    Next
    INDEX
    Explanations

    odeint, 負け, させ, Date

    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
     hours
    -2.28
     Hours
    -1.95
    Hours
    -1.77
     HOURS
    -1.65
    hours
    -1.55
    HOURS
    -1.27
     horas
    -1.26
     heures
    -1.13
     hour
    -1.09
    Horas
    -1.09
    POSITIVE LOGITS
    ed
    0.94
    rr
    0.84
    ts
    0.82
    guess
    0.73
    taa
    0.73
    лян
    0.73
    wf
    0.72
    imo
    0.72
    wat
    0.71
    られた
    0.71
    Activations Density 0.026%

    No Known Activations