© 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-65K
    7. 52811
    Prev
    Next
    INDEX
    Explanations

    "ND" abbreviations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     aud
    0.38
    ッド
    0.38
    ッサ
    0.38
    لد
    0.35
    மைப்பு
    0.35
     тока
    0.35
    }^{*}\
    0.35
    ற
    0.35
    告诉
    0.34
    enskap
    0.34
    POSITIVE LOGITS
     ND
    0.57
    ND
    0.48
     NDR
    0.43
     NDP
    0.40
    bele
    0.39
    лід
    0.39
     NDA
    0.39
    UTONIUM
    0.39
     marinated
    0.38
    Peq
    0.38
    Activations Density 0.017%

    No Known Activations