© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7363
    Prev
    Next
    INDEX
    Explanations

    multi-year durations and events

    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_10/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
     of
    -3.05
     "
    -2.28
     his
    -2.25
    主催
    -2.14
     
    -2.06
     The
    -1.98
     pôr
    -1.93
     to
    -1.91
     It
    -1.91
     entscheid
    -1.90
    POSITIVE LOGITS
    ቼ
    2.27
    ‘
    2.23
    ie
    2.20
    焢
    2.11
    ’，
    2.05
    őtt
    2.03
    糴
    2.03
     (‘
    2.03
    伱
    2.03
    ława
    2.00
    Activations Density 0.040%

    No Known Activations