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. 17-GEMMASCOPE-2-RES-65K
    4. 47409
    Prev
    Next
    INDEX
    Explanations

    peace be with you

    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_17_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
     thaw
    1.03
     censor
    1.01
    Ӏ
    0.98
    С
    0.98
    ي
    0.96
    Verse
    0.94
     গোলাম
    0.94
    ালা
    0.94
    ombrie
    0.93
     lateribus
    0.92
    POSITIVE LOGITS
    ้
    1.33
    পতি
    1.21
    ro
    1.19
    ting
    1.18
    ست
    1.16
    એ
    1.12
    themed
    1.06
     آموز
    1.05
     развед
    1.02
    utiérrez
    1.02
    Activations Density 0.003%

    No Known Activations