© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13814
    Prev
    Next
    INDEX
    Explanations

    make it small `condition` `helpers`

    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
     iteration
    0.41
     %+
    0.40
     palliative
    0.38
     TIR
    0.37
    tir
    0.37
    rir
    0.36
     iterative
    0.35
    works
    0.35
    とする
    0.35
    temporal
    0.35
    POSITIVE LOGITS
    epad
    0.45
    andang
    0.40
     dáng
    0.39
    峋
    0.38
    ciano
    0.38
     flywheel
    0.37
    ळ्या
    0.37
     Veja
    0.37
     യാത്ര
    0.37
    ตรฐาน
    0.37
    Activations Density 0.000%

    No Known Activations