© 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. 16-GEMMASCOPE-2-RES-262K
    7. 16379
    Prev
    Next
    INDEX
    Explanations

    code repository

    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_16_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
     employés
    0.93
     hôtels
    0.93
    oció
    0.90
     Иң
    0.90
     procédés
    0.89
    అ
    0.88
    },
    0.87
    ن
    0.85
     Télé
    0.84
    ン
    0.84
    POSITIVE LOGITS
    k
    1.25
    ul
    1.13
    b
    1.13
    ov
    1.11
    า
    1.06
    ן
    1.05
    w
    1.00
    p
    1.00
    of
    0.97
    lar
    0.97
    Activations Density 0.004%

    No Known Activations