© 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. 29447
    Prev
    Next
    INDEX
    Explanations

    content type / MIME type

    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
    vnd
    0.53
    现代化
    0.49
    保存
    0.42
     dateFormat
    0.42
     dard
    0.41
     மொழ
    0.40
    送り
    0.40
    价
    0.39
     язы
    0.39
    อายุ
    0.39
    POSITIVE LOGITS
     seashore
    0.38
    mino
    0.38
     peels
    0.38
     nutritive
    0.36
     pore
    0.36
     ascertained
    0.34
    defineProperty
    0.34
    lamp
    0.34
     cautious
    0.34
     texture
    0.33
    Activations Density 0.002%

    No Known Activations