© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6048
    Prev
    Next
    INDEX
    Explanations

    distinguishes or differentiates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ੩
    0.48
     stirring
    0.40
    叢
    0.40
    <0x89>
    0.39
     negotiation
    0.39
     prisão
    0.39
     scoping
    0.39
     lending
    0.39
     kidnapping
    0.39
     sidelines
    0.38
    POSITIVE LOGITS
     сол
    0.53
     eluted
    0.47
     ಯಾವುದೇ
    0.46
     товары
    0.46
     или
    0.46
    socket
    0.46
    螭
    0.46
     cinereo
    0.44
     пожалуйста
    0.44
     отобра
    0.44
    Activations Density 0.004%

    No Known Activations