© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7586
    Prev
    Next
    INDEX
    Explanations

    `encode('utf-8')` or `open(`

    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
    /*.
    0.78
    зумі
    0.74
     about
    0.74
    置
    0.69
     authenticate
    0.68
    =/
    0.68
    Mia
    0.67
     indist
    0.67
    炇
    0.67
    丄
    0.67
    POSITIVE LOGITS
    ('
    1.73
     '
    1.72
     ('
    1.55
     ‘
    1.48
     ['
    1.43
    ='
    1.38
     "
    1.28
    ("
    1.28
    ['
    1.26
     `'
    1.23
    Activations Density 0.105%

    No Known Activations