Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8280
    Prev
    Next
    INDEX
    Explanations

    's [action verb]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     largas
    1.96
     elucid
    1.77
    ну
    1.73
    ﺐ
    1.70
    یا
    1.65
    лар
    1.64
     denounced
    1.63
     опреде
    1.59
     selves
    1.58
     FRP
    1.55
    POSITIVE LOGITS
    s
    1.88
    tidak
    1.82
    ptăm
    1.73
     الصحية
    1.68
    ők
    1.64
    ito
    1.63
    ändige
    1.57
    ifiably
    1.56
    υ
    1.55
    ות
    1.50
    Activations Density 0.114%

    No Known Activations