© 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. 13071
    Prev
    Next
    INDEX
    Explanations

    navigating Resource

    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
    ri
    0.55
     Elements
    0.45
    i
    0.44
    ie
    0.44
    ail
    0.44
     Lite
    0.43
    ol
    0.43
     dedicated
    0.42
     MOT
    0.42
     পাবে
    0.42
    POSITIVE LOGITS
     ){
    0.48
    స
    0.48
    ,)
    0.47
    Вер
    0.46
     ácido
    0.46
     направления
    0.45
     فِي
    0.45
    នៅក្នុង
    0.45
    )【
    0.45
    𝘋
    0.45
    Activations Density 0.006%

    No Known Activations