© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99464
    Prev
    Next
    INDEX
    Explanations

    describing objects or body parts

    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_34/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
     that
    -1.24
     to
    -1.08
     usando
    -1.05
     using
    -1.05
     by
    -1.01
    kurat
    -0.98
     looming
    -0.97
    ที่จะ
    -0.96
     чтобы
    -0.90
     raging
    -0.90
    POSITIVE LOGITS
     like
    2.61
    like
    1.35
    Like
    1.34
     causing
    1.31
     Like
    1.30
     from
    1.19
     LIKE
    1.19
    像
    1.18
    ทำให้
    1.16
     creating
    1.16
    Activations Density 0.073%

    No Known Activations