© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 6856
    Prev
    Next
    INDEX
    Explanations

    Plotting and linear layers

    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_all/layer_41_width_262k_l0_big
    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
    physiological
    0.38
    าท
    0.35
    َي
    0.35
    estay
    0.35
    ッピング
    0.33
    รรม
    0.33
    apoptotic
    0.33
    َان
    0.32
    <unused402>
    0.32
    ើយ
    0.31
    POSITIVE LOGITS
    >(
    0.36
            
    0.34
    (
    0.32
    6
    0.31
    **(
    0.31
     Die
    0.31
    3
    0.30
    出现在
    0.30
     컨
    0.30
    Later
    0.29
    Activations Density 0.009%

    No Known Activations