© 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. 31-GEMMASCOPE-2-RES-262K
    7. 56820
    Prev
    Next
    INDEX
    Explanations

    building blocks

    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_31_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
    2
    0.50
     dismal
    0.47
     vicious
    0.45
     reliever
    0.44
     pada
    0.43
    به
    0.42
    ন্ত্রণাল
    0.41
     depressing
    0.41
    민
    0.40
     dig
    0.40
    POSITIVE LOGITS
     composing
    0.61
    构建
    0.60
     Compose
    0.57
    组成
    0.56
     Compos
    0.56
     underpinning
    0.55
     构建
    0.54
    构成
    0.53
     compone
    0.53
     bricks
    0.52
    Activations Density 0.018%

    No Known Activations