© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25489
    Prev
    Next
    INDEX
    Explanations

    voucher, waiver, varchar

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    n
    -2.70
    儅
    -2.48
     ใน
    -2.28
    푔
    -2.25
    ⣉
    -2.25
    嚒
    -2.23
    u
    -2.22
    ᡨ
    -2.20
     любви
    -2.19
    l
    -2.17
    POSITIVE LOGITS
     "
    2.50
    <td>
    2.19
     of
    2.16
    <bos>
    2.08
    店長
    2.05
     
    2.05
     et
    2.03
    …"
    2.03
     ("
    2.03
    --"
    2.02
    Activations Density 0.004%

    No Known Activations