© 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. 13127
    Prev
    Next
    INDEX
    Explanations

    detach and detachment

    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
    ⬮
    -3.13
    渽
    -2.63
     arduous
    -2.45
     península
    -2.41
     Berlín
    -2.38
    遒
    -2.36
    鲠
    -2.34
     短发
    -2.30
    黢
    -2.30
    鈈
    -2.28
    POSITIVE LOGITS
    2
    2.91
    —
    2.67
    </td>
    2.55
    --
    2.55
    ’
    2.50
    ",
    2.48
    ちなみに
    2.44
     I
    2.41
    </b>
    2.39
    ),
    2.34
    Activations Density 0.003%

    No Known Activations