© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8525
    Prev
    Next
    INDEX
    Explanations

    npower payment

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

    import numpy as np

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adur
    0.46
    yang
    0.46
    Sparse
    0.45
    mson
    0.44
    肋
    0.42
    agnes
    0.40
    dinitro
    0.40
    panel
    0.39
    Solar
    0.39
    ėj
    0.39
    POSITIVE LOGITS
     arrays
    0.48
     random
    0.45
     arr
    0.44
    [:,
    0.44
     array
    0.42
     Arrays
    0.42
    ndarray
    0.41
     brachte
    0.41
     exchange
    0.41
     }=
    0.40
    Activations Density 0.013%

    No Known Activations