© 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. 99581
    Prev
    Next
    INDEX
    Explanations

    that may

    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
     probably
    -1.32
     Probably
    -1.17
     will
    -1.09
     still
    -1.03
     certainly
    -0.99
     likely
    -0.97
     or
    -0.96
     it
    -0.95
     most
    -0.95
     usually
    -0.95
    POSITIVE LOGITS
    might
    2.17
     may
    2.14
    Might
    1.97
     might
    1.88
    may
    1.70
     Might
    1.55
     MIGHT
    1.42
    May
    1.41
     ممکن
    1.25
     May
    1.18
    Activations Density 0.029%

    No Known Activations