© 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. 41056
    Prev
    Next
    INDEX
    Explanations

    dates and locations

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

    end-to-end encryption and ethical considerations

    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
    要么
    0.43
    ॉर्ट
    0.41
     स्टूडेंट
    0.40
    ัต
    0.40
     विद्यार्थ्या
    0.40
    {}
    0.39
     άλ
    0.39
    ‼
    0.39
     छात्र
    0.39
    ądź
    0.39
    POSITIVE LOGITS
     inbuilt
    0.48
     hardships
    0.46
     obligations
    0.45
     justiciable
    0.45
    دخل
    0.44
     الاولى
    0.43
     hechos
    0.42
     aforesaid
    0.42
     judiciales
    0.41
    عاد
    0.40
    Activations Density 0.000%

    No Known Activations