© 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. 99209
    Prev
    Next
    INDEX
    Explanations

    charcoal and Becky

    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
    </b>
    -3.28
    en
    -3.09
    end
    -2.75
    .”
    -2.61
    (
    -2.45
    ">
    -2.44
    2
    -2.42
    9
    -2.42
    replyreport
    -2.33
     ‘
    -2.31
    POSITIVE LOGITS
    屃
    2.91
    蟜
    2.64
    </h3>
    2.58
    ⃨
    2.48
     墊
    2.31
    蹋
    2.25
    .
    2.23
     pensamos
    2.16
     Utilizamos
    2.16
     poté
    2.14
    Activations Density 0.002%

    No Known Activations