© 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. 87090
    Prev
    Next
    INDEX
    Explanations

    email sending timestamp

    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
    hla
    -0.80
     perquè
    -0.77
     gwiazd
    -0.75
    ▿
    -0.72
     Poids
    -0.69
    轎
    -0.69
    γραμμα
    -0.69
     rodzin
    -0.69
    füh
    -0.69
     sonic
    -0.69
    POSITIVE LOGITS
    Sent
    5.34
     Sent
    4.47
     sent
    4.41
    sent
    3.73
     SENT
    2.88
    Enviado
    2.70
    SENT
    2.70
     despatched
    2.59
     dispatched
    2.56
     envoyé
    2.42
    Activations Density 0.032%

    No Known Activations