© 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. 102581
    Prev
    Next
    INDEX
    Explanations

    overrun, hydroxide, abort

    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
    When
    -2.59
     aksesuar
    -2.48
     menyen
    -2.28
    )
    -2.28
     套装
    -2.22
     sabun
    -2.22
    ～～～～
    -2.20
    ᡝ
    -2.16
    Compared
    -2.14
     Stupid
    -2.13
    POSITIVE LOGITS
    ↵
    4.25
    n
    2.89
    </h3>
    2.56
    拶
    2.53
     ‘‘
    2.53
    pulseira
    2.44
    ?’
    2.44
     untuk
    2.41
    l
    2.41
    le
    2.31
    Activations Density 0.004%

    No Known Activations