© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7456
    Prev
    Next
    INDEX
    Explanations

    `Ptr`, `shared_ptr`, `RefPtr`, `function`

    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
    .
    -1.91
     “
    -1.48
     but
    -1.45
     return
    -1.44
     To
    -1.43
     natürlich
    -1.38
     
    -1.38
     encontre
    -1.33
    してます
    -1.30
    熥
    -1.29
    POSITIVE LOGITS
    䉴
    1.58
     opérés
    1.56
    勠
    1.53
    我们
    1.50
     事例
    1.47
     of
    1.45
     mengangg
    1.41
    vám
    1.39
     チラシ
    1.38
     meraih
    1.34
    Activations Density 0.012%

    No Known Activations