© 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. 98597
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and editions

    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
    owsky
    -0.83
    Today
    -0.81
     limitaciones
    -0.78
    Fifteen
    -0.78
     hold
    -0.77
     when
    -0.76
     father
    -0.75
     held
    -0.75
     know
    -0.74
     played
    -0.73
    POSITIVE LOGITS
     second
    3.05
     third
    2.81
     fifth
    2.67
     fourth
    2.67
    second
    2.53
     sixth
    2.52
    third
    2.48
    fourth
    2.47
    fifth
    2.38
    Second
    2.28
    Activations Density 0.072%

    No Known Activations