© 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. 59606
    Prev
    Next
    INDEX
    Explanations

    I'd or you'd followed by a verb

    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
    on
    -2.59
    </strong>
    -2.56
    ㆆ
    -2.44
    ꜆
    -2.36
    y
    -2.30
    呖
    -2.19
    籏
    -2.11
    媖
    -2.11
    </h3>
    -2.09
    r
    -2.02
    POSITIVE LOGITS
     be
    2.83
    $
    2.48
    鸯
    2.27
     aktuelle
    2.16
    裥
    2.11
     Our
    2.03
     Arkivert
    1.80
     lidí
    1.73
    Ⴈ
    1.73
     they
    1.73
    Activations Density 0.012%

    No Known Activations