© 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. 10-GEMMASCOPE-RES-131K
    7. 38362
    Prev
    Next
    INDEX
    Explanations

    Internal Revenue Service cases with "v."

    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
    Negative Logits
    _
    -1.56
    </sup>
    -1.30
    \_
    -1.30
    änemark
    -1.25
    比起
    -1.25
    おはよう
    -1.24
    イケメン
    -1.23
    訃
    -1.23
    8
    -1.23
    摹
    -1.22
    POSITIVE LOGITS
     tax
    1.27
    pisode
    1.23
     Taxes
    1.22
     njego
    1.20
    hemm
    1.16
     bram
    1.13
     vā
    1.12
    rages
    1.10
    UCN
    1.09
     Taxation
    1.09
    Activations Density 0.046%

    No Known Activations