© 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. 113437
    Prev
    Next
    INDEX
    Explanations

    gifts, seat, berth, diet

    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
    捋
    -1.62
    跺
    -1.59
    変わる
    -1.53
    ⸨
    -1.48
    ୦
    -1.48
     discerning
    -1.45
     inspirada
    -1.45
     acontec
    -1.45
     =(
    -1.44
     what
    -1.42
    POSITIVE LOGITS
    this
    1.82
    6
    1.70
    These
    1.63
     pasirink
    1.56
    since
    1.55
    都
    1.54
    ی
    1.50
     wußte
    1.50
    This
    1.49
    ਰਾ
    1.47
    Activations Density 0.057%

    No Known Activations