© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134887
    Prev
    Next
    INDEX
    Explanations

    lists and numbers

    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
     непотпу
    0.43
     indigenous
    0.42
     школова
    0.38
    ptor
    0.38
     концерт
    0.37
    ኞ
    0.35
     swimwear
    0.35
     старије
    0.34
     ори
    0.34
    itumor
    0.34
    POSITIVE LOGITS
    βά
    0.40
    más
    0.39
    מן
    0.39
     என்கிற
    0.39
    macd
    0.38
    nader
    0.38
    SCHRAMM
    0.38
    ECH
    0.37
    
    0.37
     """
    0.37
    Activations Density 0.031%

    No Known Activations