© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 212309
    Prev
    Next
    INDEX
    Explanations

    scientific and theoretical concepts

    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
    Τ
    0.39
    荅
    0.39
     Dí
    0.38
    笳
    0.37
    禛
    0.37
    дея
    0.37
    Pit
    0.36
    าด
    0.36
    medic
    0.36
    篝
    0.36
    POSITIVE LOGITS
     ماده
    0.41
     namani
    0.40
    burne
    0.40
    faite
    0.39
     puffs
    0.38
    Wnd
    0.38
    態
    0.38
    ,#
    0.37
     controllers
    0.36
     cranks
    0.36
    Activations Density 0.000%

    No Known Activations