© 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. 21517
    Prev
    Next
    INDEX
    Explanations

    Garland Science, incandescent bulbs

    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
    k
    -3.30
    n
    -3.05
    </strong>
    -2.88
    ay
    -2.86
    p
    -2.77
    d
    -2.70
    om
    -2.61
    w
    -2.59
    すすめ
    -2.58
    튿
    -2.58
    POSITIVE LOGITS
    This
    3.25
    When
    2.53
    With
    2.53
    angkap
    2.50
    These
    2.50
    While
    2.39
    During
    2.33
     These
    2.31
    Since
    2.28
     Menggunakan
    2.27
    Activations Density 0.012%

    No Known Activations