© 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. 39463
    Prev
    Next
    INDEX
    Explanations

    software updates

    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
     through
    -2.27
     by
    -2.25
     with
    -2.22
     one
    -2.14
     Even
    -1.91
     various
    -1.90
     out
    -1.89
    of
    -1.88
    at
    -1.85
     an
    -1.84
    POSITIVE LOGITS
     !!!!
    2.06
    跸
    1.98
     adesi
    1.97
     semelh
    1.94
     安装
    1.92
    ⟣
    1.91
     ſont
    1.90
     sooo
    1.88
     soooo
    1.88
    冖
    1.88
    Activations Density 0.025%

    No Known Activations