© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12729
    Prev
    Next
    INDEX
    Explanations

    progress and improvement

    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_31_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
     Require
    0.46
     requires
    0.46
     need
    0.45
     disturbed
    0.44
     આવશે
    0.44
     conflicting
    0.42
     disturbance
    0.42
     չ
    0.42
     delicate
    0.41
     szüks
    0.41
    POSITIVE LOGITS
     improvements
    1.03
    improvements
    0.96
     achievements
    0.96
     mejoras
    0.95
    改善
    0.94
    improved
    0.93
     logros
    0.93
     개선
    0.92
     improved
    0.89
     mejora
    0.89
    Activations Density 0.082%

    No Known Activations