© 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-65K
    7. 486
    Prev
    Next
    INDEX
    Explanations

    identifying relevant search terms

    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_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
     ប
    0.46
     HomeScreen
    0.45
    靂
    0.44
     doprav
    0.44
     fireball
    0.44
    驅
    0.43
    İR
    0.43
     paraly
    0.43
    ស្ថ
    0.43
    <unused48>
    0.42
    POSITIVE LOGITS
     things
    0.41
    laid
    0.41
     deadlines
    0.41
    grad
    0.40
     all
    0.40
    ol
    0.40
     they
    0.38
     it
    0.38
    pl
    0.38
     seas
    0.38
    Activations Density 0.008%

    No Known Activations