© 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. 120104
    Prev
    Next
    INDEX
    Explanations

    formation

    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
    ка
    1.03
    两
    0.95
    とに
    0.94
    он
    0.89
    TimeSeries
    0.88
    henyl
    0.88
    例文帳に追加
    0.86
    ü
    0.86
    が一
    0.84
    YE
    0.83
    POSITIVE LOGITS
    ج
    1.31
     Formation
    1.23
     formation
    1.21
    सँग
    1.18
    m
    1.17
    ac
    1.15
    et
    1.13
    u
    1.11
    ه
    1.11
    트
    1.07
    Activations Density 0.009%

    No Known Activations