© 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. 1301
    Prev
    Next
    INDEX
    Explanations

    Japanese, Korean, Tamil

    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
    িনবার্গ
    0.23
     as
    0.23
    㫻
    0.22
    ઉન
    0.22
    觕
    0.21
     streamlining
    0.21
     notor
    0.21
    砳
    0.21
     incompl
    0.20
    㓡
    0.20
    POSITIVE LOGITS
    aya
    0.23
    ok
    0.22
    akan
    0.22
    ara
    0.22
    iya
    0.22
    ya
    0.21
    anyaan
    0.21
    oka
    0.21
    asa
    0.20
    azan
    0.20
    Activations Density 0.166%

    No Known Activations