© 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. 166467
    Prev
    Next
    INDEX
    Explanations

    namespace names

    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
     Beet
    0.46
     Waves
    0.44
    AO
    0.43
     AO
    0.42
     Trident
    0.41
     Corso
    0.39
     स्क्रब
    0.38
    万
    0.38
     propagating
    0.38
    Ao
    0.38
    POSITIVE LOGITS
    Registry
    0.43
     домаћинствима
    0.41
    ":"","
    0.41
     ("
    0.40
     حديث
    0.40
    Translated
    0.40
     عد
    0.39
     одну
    0.39
     translated
    0.38
     translations
    0.38
    Activations Density 0.003%

    No Known Activations