© 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. 40-GEMMASCOPE-2-RES-262K
    7. 211972
    Prev
    Next
    INDEX
    Explanations

    import, const, mirroring, public, illustrate

    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
    ઐ
    0.44
    
    0.43
     ಇಲ್ಲಿ
    0.43
     कब
    0.42
    ปี
    0.42
     saturate
    0.41
     сильно
    0.40
     intensively
    0.40
    何时
    0.40
     žal
    0.40
    POSITIVE LOGITS
     once
    0.42
     Once
    0.41
     One
    0.41
     P
    0.41
     variations
    0.40
    dealing
    0.39
     Opt
    0.38
    once
    0.38
    Once
    0.38
     Human
    0.37
    Activations Density 0.000%

    No Known Activations