© 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. 91023
    Prev
    Next
    INDEX
    Explanations

    time spans or quantities

    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
    整个
    -1.09
    至少
    -1.05
     whole
    -1.04
    直到
    -1.00
     atleast
    -0.99
     entire
    -0.99
     plusieurs
    -0.96
    Hundreds
    -0.89
    abinieri
    -0.88
    several
    -0.87
    POSITIVE LOGITS
     less
    1.62
    不到
    1.59
     just
    1.56
    短短
    1.55
     only
    1.52
     weniger
    1.40
     tylko
    1.37
    เพียง
    1.32
     apenas
    1.30
    わずか
    1.28
    Activations Density 0.038%

    No Known Activations