© 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. 109325
    Prev
    Next
    INDEX
    Explanations

    don't want to

    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
     방법에
    0.58
    ylated
    0.57
     [
    0.56
    omania
    0.56
    zier
    0.55
    zes
    0.55
    zi
    0.55
    :
    0.54
    方法は
    0.53
    сь
    0.52
    POSITIVE LOGITS
    Orth
    0.55
     fearing
    0.55
    aéroport
    0.54
    कोरोना
    0.53
     نیند
    0.53
    监控
    0.52
    译
    0.52
     galloping
    0.51
     overseeing
    0.51
    जानिए
    0.51
    Activations Density 0.025%

    No Known Activations