© 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. 166834
    Prev
    Next
    INDEX
    Explanations

    technical keywords and their contexts

    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
     rehab
    0.43
     desaparecido
    0.40
     مفه
    0.40
     aqua
    0.39
     pares
    0.39
    埙
    0.39
     disparu
    0.39
     abortion
    0.39
    šie
    0.39
    这就是
    0.38
    POSITIVE LOGITS
    Downloaded
    0.38
    PRE
    0.36
     Firstly
    0.36
     бор
    0.35
    swer
    0.34
    shed
    0.34
     OTHER
    0.34
    Ngày
    0.34
     //#
    0.34
          
    0.34
    Activations Density 0.000%

    No Known Activations