© 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. 143465
    Prev
    Next
    INDEX
    Explanations

    questions about legitimacy or tax

    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
    繁忙時間
    0.50
    رجال
    0.49
     namani
    0.48
    рел
    0.46
     `'\\
    0.46
    myfaces
    0.45
     जोड़ों
    0.45
    لاميذ
    0.45
    bani
    0.45
    holi
    0.44
    POSITIVE LOGITS
     tax
    0.54
     taxable
    0.51
     integer
    0.51
     subject
    0.50
     [
    0.49
     for
    0.49
     profit
    0.48
     abstract
    0.46
     agreement
    0.46
     alert
    0.46
    Activations Density 0.001%

    No Known Activations