© 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. 23796
    Prev
    Next
    INDEX
    Explanations

    maybe, perhaps, possibility

    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
     would
    -0.87
     Electrochemical
    -0.86
     australiano
    -0.85
    chnung
    -0.85
    vanja
    -0.84
    씹
    -0.83
     خواهیم
    -0.82
    ịch
    -0.82
     dava
    -0.81
     Firms
    -0.81
    POSITIVE LOGITS
    Maybe
    0.93
     maybe
    0.88
     wieder
    0.85
    perhaps
    0.83
    selling
    0.83
     apenas
    0.82
     parfois
    0.81
    pektrum
    0.81
     vielleicht
    0.81
    maybe
    0.81
    Activations Density 0.001%

    No Known Activations