© 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. 10-GEMMASCOPE-RES-131K
    7. 99434
    Prev
    Next
    INDEX
    Explanations

    dramatically change

    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
    Not in Any Lists

    No Comments

    Negative Logits
    replyreport
    -2.78
    GEBUR
    -2.53
    黽
    -2.23
    ⢊
    -2.22
    也有
    -2.22
    …’
    -2.13
    ⑉
    -2.11
    琑
    -2.11
    ଢ
    -2.11
    蠖
    -2.09
    POSITIVE LOGITS
    .
    2.86
    '
    2.42
     behulp
    2.09
    ...
    2.00
    </h4>
    1.94
    などなど
    1.94
    ),
    1.92
    ?
    1.91
    </td>
    1.81
    屜
    1.73
    Activations Density 0.007%

    No Known Activations