© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32189
    Prev
    Next
    INDEX
    Explanations

    what i'm saying

    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
     mentioned
    -0.86
     Mentioned
    -0.86
     determines
    -0.83
    かどうか
    -0.83
     decides
    -0.83
     mentre
    -0.81
     determination
    -0.81
     Bestimmungen
    -0.80
     discusses
    -0.78
     contenuto
    -0.76
    POSITIVE LOGITS
     saying
    1.32
     trying
    1.09
     Saying
    1.08
     hinting
    0.94
    saying
    0.91
     implying
    0.88
     suggesting
    0.85
     స
    0.85
    essayer
    0.85
     conveying
    0.85
    Activations Density 0.030%

    No Known Activations