© 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-65K
    7. 49414
    Prev
    Next
    INDEX
    Explanations

    defined, presented, included, dependency, Resonance

    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_65k_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
     ܐ
    0.54
     distinctly
    0.47
    illae
    0.46
    raviolet
    0.45
    iflor
    0.44
    ?”
    0.44
    aturally
    0.44
    ivation
    0.44
     epithelial
    0.44
    labels
    0.43
    POSITIVE LOGITS
     cheaper
    0.50
    闿
    0.49
     rules
    0.46
    ᱘
    0.46
     Биз
    0.46
    َاب
    0.44
     приорите
    0.43
     модерни
    0.43
    อาจ
    0.43
     penyeleng
    0.42
    Activations Density 0.069%

    No Known Activations