© 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. 68006
    Prev
    Next
    INDEX
    Explanations

    polls and polling

    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
    ’
    -2.92
    In
    -2.84
     *
    -2.48
     \
    -2.47
     monumental
    -2.39
    autogui
    -2.27
     idyllic
    -2.19
     â
    -2.14
     disdain
    -2.08
     «
    -2.06
    POSITIVE LOGITS
    釙
    2.67
    沺
    2.59
    釭
    2.59
    
    2.58
    the
    2.55
    ⸨
    2.50
     dalamnya
    2.42
    龱
    2.39
     itſelf
    2.39
     porsi
    2.36
    Activations Density 0.009%

    No Known Activations