© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47617
    Prev
    Next
    INDEX
    Explanations

    you know

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ᄈ
    0.41
    彙
    0.40
    OLIS
    0.40
     არა
    0.39
    ।...
    0.39
    cieron
    0.39
    olis
    0.38
    邱
    0.38
    !}
    0.37
     ვერ
    0.37
    POSITIVE LOGITS
    Кли
    0.43
     zoals
    0.40
    pant
    0.40
     like
    0.39
    General
    0.38
    Setelah
    0.37
     when
    0.37
    ಿಸಲು
    0.37
    <0xCB>
    0.37
    </li>
    0.37
    Activations Density 0.009%

    No Known Activations