© 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. 39635
    Prev
    Next
    INDEX
    Explanations

    things that are overlooked

    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
     If
    -3.30
    )
    -2.64
     It
    -2.63
     Such
    -2.58
     to
    -2.53
     When
    -2.50
     Should
    -2.47
    PopMatrix
    -2.42
     Если
    -2.39
    =
    -2.36
    POSITIVE LOGITS
    寕
    2.97
    pulseira
    2.94
    媜
    2.86
    ୩
    2.78
    鸶
    2.58
    ↵
    2.58
    檍
    2.58
    ୌ
    2.53
    咵
    2.52
     overlooked
    2.50
    Activations Density 0.002%

    No Known Activations