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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 1311
    Prev
    Next
    INDEX
    Explanations

    caught, overwhelmed, left, haunted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    澡
    0.81
    Resol
    0.70
    грани
    0.70
    它
    0.69
    亗
    0.68
    он
    0.67
    ્યું
    0.67
    ثل
    0.67
    发
    0.67
     مہارت
    0.66
    POSITIVE LOGITS
     unable
    1.11
     unaware
    1.06
     speechless
    1.06
     شدم
    1.05
     helpless
    1.05
     helplessly
    1.04
     adrift
    0.96
     spiritually
    0.95
     bewildered
    0.94
     financially
    0.93
    Activations Density 0.356%

    No Known Activations