© 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. 31-GEMMASCOPE-2-RES-262K
    4. 107962
    Prev
    Next
    INDEX
    Explanations

    ages, speed, body, model, resilience

    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
    IDENTAL
    0.43
    Одно
    0.42
    వ్ర
    0.42
    ִי
    0.41
     latar
    0.41
    Нау
    0.41
    Пу
    0.40
    诌
    0.40
     selam
    0.40
    ડે
    0.40
    POSITIVE LOGITS
    رويج
    0.42
     enclave
    0.41
     مدينه
    0.41
     jub
    0.40
     repl
    0.39
    智能
    0.39
     Ahu
    0.38
     enjoying
    0.38
    opically
    0.38
    ဌ
    0.38
    Activations Density 0.006%

    No Known Activations