© 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. 200756
    Prev
    Next
    INDEX
    Explanations

    disclaimer instructions technology

    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
    the
    0.50
    INOIS
    0.46
    extremely
    0.46
    να
    0.45
    active
    0.43
    directly
    0.43
    實
    0.42
    direct
    0.42
    immune
    0.42
    avoid
    0.42
    POSITIVE LOGITS
    绦
    0.47
     Valves
    0.47
     ere
    0.46
     Filters
    0.44
     Chemicals
    0.43
     Fragments
    0.43
     Strept
    0.42
     Vegetables
    0.42
     Streaming
    0.41
    ui
    0.41
    Activations Density 0.006%

    No Known Activations