© 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-16K
    7. 11368
    Prev
    Next
    INDEX
    Explanations

    numbers and amounts

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

    code delimiters, numbers, punctuation

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     I
    0.44
     P
    0.44
     N
    0.43
     A
    0.43
     M
    0.43
     R
    0.43
     x
    0.43
    x
    0.43
     D
    0.42
     S
    0.42
    POSITIVE LOGITS
    GEBURTS
    0.38
    StillWater
    0.38
    Countryside
    0.38
    assaytype
    0.38
    <unused67>
    0.37
    thisTrack
    0.37
    <unused95>
    0.37
    <unused25>
    0.35
    𒊩
    0.35
    숯
    0.35
    Activations Density 0.044%

    No Known Activations