© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 136361
    Prev
    Next
    INDEX
    Explanations

    Samoa and Uso

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (\
    0.45
     bou
    0.40
    迷
    0.39
    emaakt
    0.39
    Bou
    0.37
    iren
    0.37
    ^{\
    0.36
    akes
    0.35
     consciously
    0.35
     komb
    0.35
    POSITIVE LOGITS
     Samoa
    0.80
     Samo
    0.78
     Fa
    0.57
    ناد
    0.48
    🇼
    0.48
     वायरलेस
    0.44
     Фа
    0.43
     Uso
    0.43
     سام
    0.41
     カバー
    0.41
    Activations Density 0.002%

    No Known Activations