© 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. 143966
    Prev
    Next
    INDEX
    Explanations

    societal shifts

    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
    yatiti
    0.55
     downregulation
    0.51
     勺
    0.49
    ಿಯೇ
    0.49
     शुरुआ
    0.49
    𝐳
    0.49
    رسٹ
    0.48
     holiness
    0.48
    гре
    0.48
     अपॉन
    0.47
    POSITIVE LOGITS
     este
    0.66
     oficial
    0.50
    www
    0.49
    û
    0.48
     World
    0.47
    Este
    0.47
     Net
    0.47
    <start_of_image>
    0.46
     nivel
    0.46
     District
    0.46
    Activations Density 0.002%

    No Known Activations