© 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-262K
    7. 6192
    Prev
    Next
    INDEX
    Explanations

    asking what

    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_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
     она
    0.78
     он
    0.68
     вона
    0.67
     it
    0.63
     它
    0.62
    其
    0.61
     они
    0.60
    它
    0.60
    poch
    0.59
    oun
    0.59
    POSITIVE LOGITS
     does
    3.02
     did
    2.84
     do
    2.57
     Does
    2.37
    does
    2.23
    Does
    2.21
     Did
    2.19
    Did
    2.04
     are
    1.97
    did
    1.90
    Activations Density 0.297%

    No Known Activations