© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64506
    Prev
    Next
    INDEX
    Explanations

    This invention

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

    the presence of hexadecimal color codes (e.g. “#f2f2f2,” “#CBCBCB”)

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     salvajes
    -1.23
    Ď
    -1.13
    groet
    -1.13
     najczęściej
    -1.13
     fejles
    -1.11
    pios
    -1.10
     rendszer
    -1.10
     igény
    -1.09
     szerző
    -1.09
    mab
    -1.09
    POSITIVE LOGITS
    ness
    1.08
    廊下
    1.05
    ity
    1.05
    顶级
    1.05
    と思って
    1.01
    闿
    1.00
    borns
    1.00
    yness
    0.98
    ish
    0.98
    tening
    0.98
    Activations Density 0.001%

    No Known Activations