© 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. 52793
    Prev
    Next
    INDEX
    Explanations

    avoiding certain language

    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
    łop
    0.53
     [
    0.46
     riun
    0.43
     cơm
    0.43
     į
    0.42
     trou
    0.41
     grabación
    0.41
    ientemente
    0.40
    [
    0.40
     în
    0.40
    POSITIVE LOGITS
    Diagnostic
    0.52
    VENTORY
    0.44
    Companion
    0.43
    Duties
    0.43
    Thickness
    0.42
    Waste
    0.42
    Efficient
    0.41
    TabText
    0.41
     parasites
    0.41
    Lucky
    0.40
    Activations Density 0.004%

    No Known Activations