© 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. 204574
    Prev
    Next
    INDEX
    Explanations

    any order, manner, or form

    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
    í
    0.43
     liquides
    0.38
     tử
    0.37
    ួ
    0.36
     transmissão
    0.36
     vég
    0.35
    Ế
    0.35
    ká
    0.34
    広島
    0.34
    Ј
    0.34
    POSITIVE LOGITS
     форма
    0.49
     Forma
    0.46
     form
    0.42
     way
    0.40
     Format
    0.40
     формата
    0.39
     ফর্ম
    0.39
     format
    0.38
    форма
    0.38
     forma
    0.38
    Activations Density 0.001%

    No Known Activations