© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 103472
    Prev
    Next
    INDEX
    Explanations

    ninja and jutsu

    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
     Vaccination
    0.65
     Daley
    0.60
     Ursula
    0.59
     DMBT
    0.59
    데이터
    0.59
     ছিল
    0.57
    襷
    0.57
     kajian
    0.57
    DATA
    0.57
     হুগ
    0.57
    POSITIVE LOGITS
    al
    0.69
     interna
    0.54
    rence
    0.54
    il
    0.54
     internation
    0.54
    rimi
    0.53
    k
    0.52
    àn
    0.51
    d
    0.50
    super
    0.50
    Activations Density 0.006%

    No Known Activations