© 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. 98347
    Prev
    Next
    INDEX
    Explanations

    places, intersections, service

    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
    midi
    0.40
    hind
    0.39
    iniz
    0.38
    lukan
    0.38
    ásra
    0.37
    nič
    0.37
    рет
    0.37
    ŕ
    0.36
    reo
    0.36
    경제
    0.36
    POSITIVE LOGITS
     Tested
    0.41
     taiwan
    0.40
     til
    0.39
     Taiwanese
    0.39
    亚
    0.39
    亞
    0.39
     Teaching
    0.38
     couvre
    0.38
     persian
    0.38
     Bolshevik
    0.38
    Activations Density 0.001%

    No Known Activations