© 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. 500
    Prev
    Next
    INDEX
    Explanations

    preparing for models

    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
    蚊
    0.46
     สํา
    0.46
    不用
    0.45
     сорти
    0.44
    abinieri
    0.43
    少ない
    0.42
     adjacency
    0.41
     extensible
    0.41
    藪
    0.41
    hObject
    0.40
    POSITIVE LOGITS
     Best
    0.44
    Taste
    0.43
    ঙ্ক
    0.40
    缇
    0.40
     réparation
    0.39
     Tada
    0.39
    Eff
    0.38
    ======
    0.38
     যায়
    0.38
     Opp
    0.37
    Activations Density 0.000%

    No Known Activations