© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 598
    Prev
    Next
    INDEX
    Explanations

    feelings and appearance

    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
    ⿷
    0.88
     случаи
    0.86
     считаю
    0.86
     σημ
    0.80
    మిక
    0.78
    এ
    0.78
     terlihat
    0.78
     Cholesterol
    0.77
    ۞
    0.76
    我认为
    0.75
    POSITIVE LOGITS
     compelled
    1.54
     like
    1.53
     overwhelmed
    1.22
     betrayed
    1.22
     unwell
    1.20
     obligated
    1.18
    像是
    1.13
     obliged
    1.12
     threatened
    1.12
     Like
    1.11
    Activations Density 0.426%

    No Known Activations