© 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. 31-GEMMASCOPE-2-RES-262K
    4. 44590
    Prev
    Next
    INDEX
    Explanations

    iron deficiency, absorption, and sources

    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
     weave
    0.46
    Scape
    0.43
    胧
    0.42
    قیع
    0.39
    椛
    0.39
    فیلم
    0.39
    िफिकेट
    0.38
     weaving
    0.38
    稦
    0.38
    DanhMucSP
    0.38
    POSITIVE LOGITS
     iron
    1.30
     Iron
    1.17
    Iron
    1.16
     IRON
    1.12
     hierro
    1.12
     आयरन
    1.05
     الحديد
    1.03
    铁
    1.01
    鐵
    1.00
    IRON
    0.99
    Activations Density 0.030%

    No Known Activations