© 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. 100004
    Prev
    Next
    INDEX
    Explanations

    data type identifiers

    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
    łącznie
    0.42
     поступи
    0.40
     خفی
    0.39
    子里
    0.39
    ioctl
    0.38
    꿰
    0.37
     ম্যানে
    0.37
    abut
    0.36
    Joey
    0.36
    宙
    0.36
    POSITIVE LOGITS
    سل
    0.42
    मती
    0.39
    際の
    0.38
     bonuses
    0.37
    urate
    0.37
    وره
    0.37
    ENCIAS
    0.36
    ອບ
    0.36
     methionine
    0.35
     slee
    0.34
    Activations Density 0.000%

    No Known Activations