© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7151
    Prev
    Next
    INDEX
    Explanations

    points off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    ofu
    0.95
     compreender
    0.94
    Exploring
    0.90
    著作
    0.89
    从业
    0.89
     tractable
    0.87
    検討
    0.87
    汢
    0.87
    indeed
    0.87
    simeq
    0.86
    POSITIVE LOGITS
     bonus
    2.25
     bonuses
    2.15
     rewards
    2.07
     Bonus
    1.94
     Bonuses
    1.93
     reward
    1.93
     Rewards
    1.91
    Bonus
    1.89
    奖励
    1.84
     бонус
    1.75
    Activations Density 0.256%

    No Known Activations