© 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. 99213
    Prev
    Next
    INDEX
    Explanations

    such as

    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
     semelh
    -2.27
    ᥬ
    -2.19
    
    -2.06
     gewi
    -1.97
     miniaturka
    -1.96
    鼍
    -1.92
     relógio
    -1.91
     😁
    -1.91
    跩
    -1.88
     aussit
    -1.84
    POSITIVE LOGITS
     any
    2.47
     or
    2.30
     with
    2.17
    With
    2.17
     in
    2.11
     it
    2.05
     With
    2.02
     Because
    1.84
    When
    1.84
    ！！！
    1.80
    Activations Density 0.077%

    No Known Activations