© 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. 134756
    Prev
    Next
    INDEX
    Explanations

    ** with punctuation

    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
     комна
    0.46
    🧂
    0.43
    房間
    0.42
    exercise
    0.42
     exercice
    0.41
    дям
    0.41
    Translations
    0.41
     exercise
    0.40
    incare
    0.40
    🧅
    0.40
    POSITIVE LOGITS
    mohan
    0.44
     language
    0.43
    language
    0.42
     video
    0.42
    Language
    0.42
    transformers
    0.40
    video
    0.39
    ransform
    0.38
     transforms
    0.38
     Video
    0.38
    Activations Density 0.001%

    No Known Activations