© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24436
    Prev
    Next
    INDEX
    Explanations

    getting things working

    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
     فرو
    0.36
    leti
    0.36
    ராம
    0.36
     verzi
    0.36
    ✙
    0.36
    ेश्च
    0.36
    сю
    0.35
    찧
    0.35
     verw
    0.34
    ह्
    0.34
    POSITIVE LOGITS
     things
    0.57
    Things
    0.52
     rid
    0.49
     चीजें
    0.45
     everything
    0.44
    事情
    0.43
    things
    0.42
    everything
    0.41
    imleri
    0.41
     Things
    0.40
    Activations Density 0.004%

    No Known Activations