© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9250
    Prev
    Next
    INDEX
    Explanations

    magnesium

    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_16_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
    нг
    0.46
     atthakath
    0.45
    सँग
    0.40
     अंग्रे
    0.40
     umož
    0.40
    ᱱ
    0.40
    ﻋ
    0.39
    CHEMY
    0.39
    ж
    0.38
     délé
    0.38
    POSITIVE LOGITS
     has
    0.52
     will
    0.52
     is
    0.51
     can
    0.48
     have
    0.46
    over
    0.43
     for
    0.39
    ing
    0.39
     and
    0.39
     ways
    0.39
    Activations Density 0.011%

    No Known Activations