© 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. 29263
    Prev
    Next
    INDEX
    Explanations

    save code

    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
    kyt
    0.40
    beach
    0.38
    ᅲ
    0.38
    Blake
    0.38
     Blake
    0.36
    会計
    0.36
    につきまして
    0.35
     Betty
    0.35
    約束
    0.35
    col
    0.34
    POSITIVE LOGITS
     solidify
    0.49
    ively
    0.44
    uglify
    0.43
    handedly
    0.43
     iccad
    0.40
     **
    0.40
    ecd
    0.39
    पुरम
    0.39
    émico
    0.39
    ibernate
    0.39
    Activations Density 0.002%

    No Known Activations