© 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. 30655
    Prev
    Next
    INDEX
    Explanations

    area under a curve

    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
     sofas
    0.54
    ORIENTATION
    0.53
     způso
    0.49
     spô
    0.48
    мур
    0.47
    🏸
    0.46
    ដែលមាន
    0.46
     haircuts
    0.45
    GEBURTSDATUM
    0.45
     isoforms
    0.45
    POSITIVE LOGITS
    旋
    0.52
    研
    0.41
     tient
    0.41
    let
    0.41
    awaited
    0.40
    ará
    0.40
    、《
    0.39
    treating
    0.39
    risk
    0.39
    jectory
    0.38
    Activations Density 0.000%

    No Known Activations