© 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. 40-GEMMASCOPE-2-RES-262K
    4. 83940
    Prev
    Next
    INDEX
    Explanations

    describing entities and their states

    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
     ट्व
    0.44
    ສາ
    0.42
    BlockFit
    0.42
    FFFFFF
    0.41
    程度
    0.40
     ото
    0.40
    ()==
    0.40
    ATCH
    0.40
     要求
    0.39
    ᱖
    0.38
    POSITIVE LOGITS
     files
    0.41
     file
    0.40
     fund
    0.39
    Dead
    0.38
    file
    0.37
     Danny
    0.37
     prepares
    0.37
     barring
    0.36
     File
    0.36
     sulfur
    0.36
    Activations Density 0.001%

    No Known Activations