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. 29-GEMMASCOPE-2-RES-65K
    4. 41025
    Prev
    Next
    INDEX
    Explanations

    prime numbers

    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_29_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
    Wire
    0.65
    ίζ
    0.60
    ভার
    0.58
    覆
    0.57
     horizon
    0.57
     WIRE
    0.56
     Wire
    0.55
    の方が
    0.55
    /=
    0.55
    <0xE9>
    0.54
    POSITIVE LOGITS
     jovens
    0.83
     rupani
    0.81
    lesen
    0.76
    retching
    0.76
     royals
    0.76
    icrous
    0.75
     chante
    0.75
    品牌的
    0.75
     princesses
    0.75
     plagues
    0.74
    Activations Density 0.108%

    No Known Activations