© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 191259
    Prev
    Next
    INDEX
    Explanations

    describes linguistic phenomena

    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
    hanga
    0.41
     घोड़
    0.41
    ℙ
    0.41
    RefIn
    0.40
    ńskim
    0.40
    পেক্ষ
    0.39
    绶
    0.39
    叁章
    0.38
    лих
    0.38
    alanya
    0.38
    POSITIVE LOGITS
    ಟ್ಟಿ
    0.38
    자가
    0.38
    과
    0.36
     aktivitas
    0.35
     och
    0.35
     isotherms
    0.34
     suami
    0.34
    рость
    0.34
     kwa
    0.33
    izaciones
    0.33
    Activations Density 0.001%

    No Known Activations