© 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. 21114
    Prev
    Next
    INDEX
    Explanations

    attaches, attachable, centaur, renegotiation

    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
    I
    -3.84
    翃
    -2.97
    </b>
    -2.75
    .
    -2.73
     he
    -2.72
     Lately
    -2.70
     Careful
    -2.55
     nombres
    -2.45
     '
    -2.41
    ଼
    -2.38
    POSITIVE LOGITS
    </h3>
    4.50
    </strong>
    3.48
    ⃚
    3.30
    </sub>
    3.22
    al
    2.66
    AdvEx
    2.64
    "));
    2.61
    ㈰
    2.56
    pulseira
    2.55
    噐
    2.53
    Activations Density 0.026%

    No Known Activations