© 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. 195317
    Prev
    Next
    INDEX
    Explanations

    action or role followed by specific punctuation/word

    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
     <=
    0.43
     але
    0.40
     automata
    0.38
    そう
    0.38
     chic
    0.37
     program
    0.37
     прямой
    0.37
    근
    0.36
     esophageal
    0.36
     tutorials
    0.36
    POSITIVE LOGITS
     confes
    0.43
    examen
    0.42
    phobic
    0.41
    核心
    0.40
    怿
    0.40
     Piot
    0.40
    飏
    0.40
     pregunt
    0.39
    etha
    0.39
     bukanlah
    0.39
    Activations Density 0.001%

    No Known Activations