© 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. 22778
    Prev
    Next
    INDEX
    Explanations

    network programming components

    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
    賸
    -1.25
     カップ
    -1.24
    <td>
    -1.24
    ---*/
    -1.23
    らく
    -1.23
    栻
    -1.21
     thier
    -1.20
    ⦊
    -1.18
    ках
    -1.16
    jących
    -1.16
    POSITIVE LOGITS
     что
    1.31
    哟
    1.28
     gamla
    1.25
    してる
    1.24
    </h1>
    1.23
    </b>
    1.20
    を入れて
    1.20
    を入れ
    1.19
    The
    1.17
     он
    1.17
    Activations Density 0.007%

    No Known Activations