© 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. 59520
    Prev
    Next
    INDEX
    Explanations

    harrowing stories, hallowed leader, Harlow Room

    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
    W
    -2.38
    </h3>
    -2.36
    ﹶ
    -2.33
    Q
    -2.31
    B
    -2.31
    Some
    -2.22
     peruano
    -2.22
    ⡯
    -2.20
    衚
    -2.19
    Different
    -2.17
    POSITIVE LOGITS
    翃
    2.33
     maintenant
    2.22
    ܆
    2.16
    姈
    2.16
     stalwart
    2.14
     cientos
    2.13
    ῞
    2.13
    +.
    2.13
    ⏑
    2.11
    </b>
    2.09
    Activations Density 0.006%

    No Known Activations