© 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. 9508
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by diverse topics

    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
    I
    0.36
    ﺔ
    0.29
    ﻠ
    0.28
    ﻣ
    0.28
    ﻟ
    0.28
     حين
    0.27
     limpi
    0.26
    ﺧ
    0.26
    ﻥ
    0.26
    ﻫ
    0.26
    POSITIVE LOGITS
    ב
    0.35
    f
    0.33
    b
    0.32
    an
    0.32
    र
    0.29
    धर
    0.29
     hadrons
    0.29
    w
    0.27
    ર
    0.26
     arrhythmias
    0.26
    Activations Density 2.074%

    No Known Activations