© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102961
    Prev
    Next
    INDEX
    Explanations

    DOT, transportation, annotating, bully

    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
     Except
    -2.33
     Lately
    -2.22
    诸多
    -2.20
    𞤢
    -2.20
     WHAT
    -2.19
    各样的
    -2.14
     Whereas
    -2.13
     Importantly
    -2.06
    Cevap
    -2.05
    ヨーロ
    -2.05
    POSITIVE LOGITS
     envisioned
    2.42
    0
    2.33
    >
    2.30
    </td>
    2.28
    2.27
    <td>
    2.25
    ’
    2.25
    <
    2.19
    !
    2.19
     gavetas
    2.16
    Activations Density 0.002%

    No Known Activations