© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 99541
    Prev
    Next
    INDEX
    Explanations

    exon, download, Devon

    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
    傈
    0.41
    tru
    0.39
    getic
    0.38
     ভুট
    0.37
    پن
    0.37
    ሲ
    0.37
     ভুট্ট
    0.36
    堡
    0.36
     അഭി
    0.35
    тт
    0.35
    POSITIVE LOGITS
     Devon
    0.53
    Exe
    0.48
     Exo
    0.47
     Tanto
    0.43
     Electron
    0.43
     javafx
    0.43
     Brix
    0.42
     EXO
    0.41
     EXE
    0.41
     electron
    0.41
    Activations Density 0.007%

    No Known Activations