© 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. 6386
    Prev
    Next
    INDEX
    Explanations

    product, school, icon, Geraniums

    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
     Um
    0.43
    汲
    0.42
     No
    0.41
    iene
    0.41
    बरे
    0.41
    ື່
    0.40
     ഇപ്പോ
    0.40
    就
    0.39
     mittels
    0.39
    hs
    0.38
    POSITIVE LOGITS
     saws
    0.42
     його
    0.42
    зиру
    0.40
    ראל
    0.39
     तलाक
    0.38
    땄
    0.37
    жному
    0.36
     scout
    0.36
     qualcosa
    0.36
    φαλ
    0.36
    Activations Density 0.005%

    No Known Activations