© 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-65K
    7. 6050
    Prev
    Next
    INDEX
    Explanations

    creating, activating, and controlling states

    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_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
    ブログ
    0.53
     लीजिएगा
    0.51
     سیاست
    0.50
    FindingsResponse
    0.50
    𝔯
    0.49
     जोख
    0.49
     Bahkan
    0.49
     뉴스
    0.48
     Даже
    0.47
    逊
    0.47
    POSITIVE LOGITS
     activated
    0.63
     controlled
    0.62
     creates
    0.62
     electrically
    0.60
     electrons
    0.58
     magnetically
    0.57
     rotates
    0.56
     synchronously
    0.56
     stationary
    0.56
     activating
    0.55
    Activations Density 0.198%

    No Known Activations