© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6180
    Prev
    Next
    INDEX
    Explanations

    floral and herbal concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     côte
    1.23
    ség
    1.04
    ς
    1.02
     أي
    1.01
    ات
    0.98
    ीय
    0.98
    luğ
    0.96
     एल
    0.96
     पड़
    0.96
    ين
    0.95
    POSITIVE LOGITS
    ل
    1.40
     cytokinin
    1.30
     melodies
    1.27
    ли
    1.26
     bonsai
    1.24
     fibras
    1.24
     twigs
    1.23
     nomenclatura
    1.23
     parallels
    1.22
     sarees
    1.22
    Activations Density 0.189%

    No Known Activations