© 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-65K
    7. 361
    Prev
    Next
    INDEX
    Explanations

    trademarked names and entities

    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_65k_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
    rusted
    0.27
     =
    0.27
     $=
    0.27
     of
    0.25
    left
    0.25
    question
    0.25
            
    0.25
    rought
    0.25
          
    0.25
    responsibility
    0.25
    POSITIVE LOGITS
    ™,
    0.48
    ™.
    0.47
    ™
    0.45
     Ltd
    0.43
     LLC
    0.43
     llc
    0.42
    ®,
    0.42
     ™
    0.39
    ®.
    0.38
     লিমি
    0.36
    Activations Density 0.272%

    No Known Activations