© 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. 129165
    Prev
    Next
    INDEX
    Explanations

    Cuban public health system

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

    filters safety checks

    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
     tío
    0.51
     granddaughter
    0.49
     头
    0.48
     vorige
    0.47
     syndrome
    0.46
     umur
    0.46
     頭
    0.46
     z
    0.45
     হেড
    0.45
     hoofd
    0.44
    POSITIVE LOGITS
     Attempts
    0.46
    நா
    0.46
    сё
    0.46
    மக்கள்
    0.45
    явления
    0.45
    сно
    0.45
    дри
    0.44
    殚
    0.44
    Amazing
    0.44
    словия
    0.44
    Activations Density 0.000%

    No Known Activations