© 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. 4259
    Prev
    Next
    INDEX
    Explanations

    boxing and fighters

    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
     Acoust
    0.48
     মহামার
    0.46
     Bildung
    0.45
     acúst
    0.44
     NIM
    0.44
    擷
    0.43
     INSEE
    0.42
     Acoustic
    0.42
     ¶
    0.42
    }}$
    0.41
    POSITIVE LOGITS
     boxing
    1.77
     boxers
    1.54
     boxer
    1.52
    Boxing
    1.48
     fighters
    1.47
     Boxing
    1.45
    boxing
    1.41
    🥊
    1.39
     fighter
    1.28
     boxe
    1.25
    Activations Density 0.017%

    No Known Activations