© 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. 31-GEMMASCOPE-2-RES-262K
    7. 15847
    Prev
    Next
    INDEX
    Explanations

    making balloons or drugs

    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
    di
    0.51
    d
    0.51
    k
    0.50
    a
    0.49
    bab
    0.47
    i
    0.47
    unes
    0.46
    rivers
    0.46
    lymph
    0.46
     Southeast
    0.45
    POSITIVE LOGITS
    SIL
    0.47
     হয়নি
    0.45
     घेतला
    0.44
    ಲ್ಪ
    0.44
     дзяржа
    0.42
    简洁
    0.42
    PLAT
    0.40
     Dens
    0.40
    跡
    0.40
    یکم
    0.40
    Activations Density 0.002%

    No Known Activations