© 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. 10836
    Prev
    Next
    INDEX
    Explanations

    corporate offices and departments

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

    explaining how something works or what to aim for

    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
    🚱
    0.39
    enable
    0.33
     સામાન્ય
    0.33
    
    0.33
     overruled
    0.32
    想定
    0.32
    <0x80>
    0.32
     discourage
    0.30
     considérer
    0.30
    🔡
    0.30
    POSITIVE LOGITS
     বিখ্যাত
    0.48
     masterpiece
    0.45
     Cadillac
    0.43
     великолеп
    0.42
    Artista
    0.41
     mundo
    0.40
     знамени
    0.40
     artista
    0.40
     огром
    0.40
     सुपरहिट
    0.40
    Activations Density 0.000%

    No Known Activations