© 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. 82681
    Prev
    Next
    INDEX
    Explanations

    plenty of time

    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
    )²
    -0.95
    ieš
    -0.90
    tiera
    -0.90
     különböző
    -0.84
    sians
    -0.83
    thè
    -0.82
    itic
    -0.80
     McLaugh
    -0.79
    duino
    -0.79
    𝜇
    -0.78
    POSITIVE LOGITS
     plenty
    6.03
     ample
    4.75
    Plenty
    4.63
    plenty
    4.38
     Plenty
    4.38
     enough
    4.34
     sufficient
    4.22
    Enough
    3.45
     adequate
    3.44
     Ample
    3.30
    Activations Density 0.105%

    No Known Activations