© 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. 112487
    Prev
    Next
    INDEX
    Explanations

    synchrotron radiation, dialogs

    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
    0
    -3.25
    <td>
    -2.81
    焄
    -2.73
    9
    -2.55
    2
    -2.52
    鉏
    -2.31
    1
    -2.30
    豨
    -2.28
    5
    -2.23
    鋨
    -2.19
    POSITIVE LOGITS
    "
    3.66
    ’
    3.28
    ’，
    2.56
    秾
    2.42
     ſtill
    2.23
    水が
    2.23
    高达
    2.22
     imposing
    2.17
     entirety
    2.14
    while
    2.13
    Activations Density 0.001%

    No Known Activations