© 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. 40-GEMMASCOPE-2-RES-262K
    7. 119143
    Prev
    Next
    INDEX
    Explanations

    Australian adoption context

    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
     плане
    0.41
     kõr
    0.39
     патри
    0.38
    Perform
    0.38
     عالية
    0.37
     Perform
    0.37
    }/\
    0.36
    łuż
    0.36
    高
    0.36
     profane
    0.35
    POSITIVE LOGITS
     ionic
    0.49
    ition
    0.43
    mathfrak
    0.41
     المجال
    0.41
     ನೆ
    0.40
    isecond
    0.39
     squiggle
    0.39
     issus
    0.38
    شد
    0.38
     escre
    0.38
    Activations Density 0.000%

    No Known Activations