© 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. 195133
    Prev
    Next
    INDEX
    Explanations

    that allows

    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
     ჭ
    0.47
     sil
    0.43
     কোর
    0.42
     Nxf
    0.41
     Sie
    0.41
     Tract
    0.41
     laguna
    0.40
     cores
    0.40
     brz
    0.39
     renormalization
    0.39
    POSITIVE LOGITS
     scroll
    0.36
    嗡
    0.36
     البعض
    0.35
    PageComponent
    0.35
     récent
    0.35
    content
    0.34
    addSprite
    0.34
    éristiques
    0.34
    ==-
    0.34
     выну
    0.34
    Activations Density 0.003%

    No Known Activations