© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105680
    Prev
    Next
    INDEX
    Explanations

    support three

    np_acts-logits-general · gemini-2.5-flash-lite

    transfer, Raw materials, emptying, Unity, headlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erreurs
    0.62
    Diffuse
    0.49
     ignor
    0.49
     ناقص
    0.48
    ْر
    0.47
    тувати
    0.47
     ошибка
    0.47
     مطل
    0.46
     điển
    0.46
     نقصان
    0.46
    POSITIVE LOGITS
     inbound
    0.44
    t
    0.42
     state
    0.41
     onsite
    0.40
     hiking
    0.39
     Zil
    0.39
     site
    0.39
     reaffirm
    0.39
    atch
    0.38
    onRequest
    0.38
    Activations Density 0.001%

    No Known Activations