© 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. 10-GEMMASCOPE-RES-131K
    7. 70636
    Prev
    Next
    INDEX
    Explanations

    announcements and entities

    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_10/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
     if
    -3.25
     when
    -2.13
     what
    -1.98
     those
    -1.87
     innumerable
    -1.84
     poignant
    -1.78
    Numerous
    -1.68
     prevalent
    -1.64
    Often
    -1.64
    にします
    -1.61
    POSITIVE LOGITS
     also
    2.13
    s
    2.00
     этот
    1.91
     ausser
    1.74
     alltså
    1.73
     focuses
    1.67
    にも
    1.66
     queste
    1.63
    ETERS
    1.61
     этой
    1.59
    Activations Density 0.061%

    No Known Activations