© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44590
    Prev
    Next
    INDEX
    Explanations

    iron and related materials

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weave
    0.43
    ꯠ
    0.43
    蔥
    0.42
    قیع
    0.42
    quinazolin
    0.42
    獭
    0.41
    椛
    0.41
    तेश
    0.40
    栤
    0.40
    াপাশি
    0.40
    POSITIVE LOGITS
     iron
    1.41
     Iron
    1.30
     IRON
    1.28
    Iron
    1.27
     hierro
    1.17
     आयरन
    1.17
    铁
    1.16
     желез
    1.15
     الحديد
    1.13
    鐵
    1.13
    Activations Density 0.042%

    No Known Activations