© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 20278
    Prev
    Next
    INDEX
    Explanations

    Auto models and tokenizers

    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_53_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
     machines
    0.44
    Machines
    0.41
    前端
    0.38
     आना
    0.37
    詰め
    0.36
    Frog
    0.36
    聪
    0.36
    Jobs
    0.36
    bees
    0.36
    ๗
    0.36
    POSITIVE LOGITS
    or
    0.38
     যথ
    0.37
    ワク
    0.37
    description
    0.37
    ড়
    0.37
    &&
    0.36
    वाड़ी
    0.36
    クシー
    0.35
     जप
    0.34
    ora
    0.34
    Activations Density 0.000%

    No Known Activations