Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3519
    Prev
    Next
    INDEX
    Explanations

    DOIs and article identifiers

    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
     awaiting
    0.78
     lookup
    0.67
     await
    0.66
     INS
    0.63
     fu
    0.63
    ଁ
    0.63
     waiting
    0.63
     routinely
    0.61
     reeks
    0.60
     redis
    0.59
    POSITIVE LOGITS
    entreprise
    0.83
    azienda
    0.76
    organe
    0.70
    स्वास्थ्य
    0.68
    cultured
    0.66
    뽑
    0.66
     कोशिकाओं
    0.65
    gher
    0.63
    olino
    0.63
    ukunft
    0.62
    Activations Density 0.002%

    No Known Activations