© 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. 25943
    Prev
    Next
    INDEX
    Explanations

    India's president, prime minister

    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
    镜
    0.49
     bunnies
    0.48
    Discrete
    0.48
    各种
    0.47
    玹
    0.46
     Witch
    0.45
    Disk
    0.45
    𝐽
    0.44
     सावधानी
    0.44
    ালী
    0.44
    POSITIVE LOGITS
     UPSC
    0.66
     Telangana
    0.66
     Odisha
    0.65
     ಭಾರತ
    0.59
     ভারতের
    0.59
     reforms
    0.58
     Rajya
    0.58
     Jharkhand
    0.56
     India
    0.55
    প্রধানমন্ত্রী
    0.55
    Activations Density 0.016%

    No Known Activations