© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 850
    Prev
    Next
    INDEX
    Explanations

    names of people

    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_65k_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
     tangible
    0.44
     quantifiable
    0.39
     cumbersome
    0.38
     cohesive
    0.38
    ๑
    0.38
     restraints
    0.36
     grating
    0.35
     diffuse
    0.34
     extraneous
    0.34
     certainty
    0.34
    POSITIVE LOGITS
     Ç
    0.51
     D
    0.50
     H
    0.50
     Š
    0.50
     Hong
    0.49
     étaient
    0.49
     avaient
    0.49
     W
    0.48
     S
    0.47
     Singh
    0.47
    Activations Density 0.088%

    No Known Activations