Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 19624
    Prev
    Next
    INDEX
    Explanations

    fouls and cards

    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
     výbě
    0.42
    臻
    0.42
    Reli
    0.38
     නිෂ්පා
    0.38
    VELOP
    0.38
     मोठ्या
    0.38
    枃
    0.37
     στε
    0.37
    䋇
    0.37
    自信
    0.36
    POSITIVE LOGITS
     fouls
    1.40
     foul
    1.16
     penalty
    1.05
     fouling
    1.04
     penalties
    1.02
     infractions
    1.01
     fouled
    1.00
     referee
    0.99
     yellow
    0.91
     referees
    0.89
    Activations Density 0.006%

    No Known Activations