© 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. 31-GEMMASCOPE-2-RES-262K
    7. 24921
    Prev
    Next
    INDEX
    Explanations

    Python code and function definitions

    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
    谨慎
    0.40
    仹
    0.38
     procurar
    0.38
     Broward
    0.38
     Cha
    0.37
     flashed
    0.37
     météor
    0.37
    晫
    0.37
     grafted
    0.36
     período
    0.36
    POSITIVE LOGITS
    ulated
    0.52
    lementine
    0.48
    etable
    0.48
    """
    0.46
    ang
    0.46
    olines
    0.46
    ulates
    0.46
    irii
    0.46
    us
    0.45
     /ˈ
    0.45
    Activations Density 0.053%

    No Known Activations