© 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. 8953
    Prev
    Next
    INDEX
    Explanations

    ardi al

    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
    ⬐
    -2.16
     rastre
    -2.09
     mergul
    -2.03
     esbo
    -2.02
    帳に追加
    -1.98
     skóra
    -1.98
     esboço
    -1.94
     desgra
    -1.93
     portuguesa
    -1.92
    <td>
    -1.90
    POSITIVE LOGITS
    7
    2.86
    </i>
    2.75
    3
    2.63
    9
    2.56
    8
    2.41
    6
    2.33
    4
    2.19
    s
    2.19
    亖
    2.14
    e
    2.11
    Activations Density 0.001%

    No Known Activations