© 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. 119044
    Prev
    Next
    INDEX
    Explanations

    concepts, items, and measurements

    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
     Loose
    0.41
     zis
    0.41
     ያ
    0.40
     merkez
    0.40
    Lyric
    0.40
     frayed
    0.39
     RECEIPTS
    0.39
     făcut
    0.39
     અર
    0.39
    秵
    0.38
    POSITIVE LOGITS
     never
    0.42
     понятие
    0.42
    yme
    0.39
     DME
    0.39
     concept
    0.38
     conceptually
    0.38
     morally
    0.38
    문화
    0.38
    議
    0.38
    ido
    0.37
    Activations Density 0.001%

    No Known Activations