© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124551
    Prev
    Next
    INDEX
    Explanations

    Descartes seems to think than which

    np_acts-logits-general · gemini-2.5-flash-lite

    nearby avatars within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     알려
    0.44
    كشن
    0.42
     filtrar
    0.42
    ங்கா
    0.41
    影视
    0.41
    告
    0.41
    astikan
    0.41
     ఉపయోగ
    0.41
    かん
    0.41
     केंद्रीय
    0.40
    POSITIVE LOGITS
     waisted
    0.48
    ৯
    0.48
     boredom
    0.47
     inflicting
    0.45
    women
    0.43
     bored
    0.43
    peso
    0.42
     majoring
    0.42
    teenth
    0.41
    policies
    0.41
    Activations Density 0.001%

    No Known Activations