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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 512
    Prev
    Next
    INDEX
    Explanations

    government bonds

    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
     the
    0.58
     slightly
    0.57
     a
    0.56
     
    0.55
     overly
    0.52
     aka
    0.50
     agile
    0.50
    :
    0.50
     sprinkled
    0.50
     freshly
    0.50
    POSITIVE LOGITS
    CHREIBUNG
    0.59
    Lapangan
    0.58
    akaranam
    0.57
    צ
    0.57
    Gio
    0.57
    Cidade
    0.56
     Balliye
    0.56
    Pyrazole
    0.56
    viä
    0.56
    ด
    0.55
    Activations Density 0.064%

    No Known Activations