© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178199
    Prev
    Next
    INDEX
    Explanations

    there were

    np_acts-logits-general · gemini-2.5-flash-lite

    calculates Fibonacci sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Alerts
    0.48
     Colored
    0.45
     บ
    0.43
     কর্মকর্ত
    0.43
     swelled
    0.43
     мая
    0.42
    জয়
    0.42
     Epic
    0.42
    暴
    0.42
     Alert
    0.41
    POSITIVE LOGITS
    kwik
    0.51
    Staying
    0.50
     archaeological
    0.47
     inglese
    0.46
    TX
    0.46
    TING
    0.45
     archaeologist
    0.45
    Stadium
    0.44
    cure
    0.44
    p
    0.44
    Activations Density 0.000%

    No Known Activations