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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 52795
    Prev
    Next
    INDEX
    Explanations

    youtube and foreign equivalents

    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
     CAGR
    0.45
    ཋ
    0.43
     INSEE
    0.43
     সম্মিল
    0.40
    fordshire
    0.40
    ቐ
    0.40
     covariant
    0.39
    䂝
    0.39
     MNRAS
    0.38
    奂
    0.38
    POSITIVE LOGITS
     youtube
    0.67
    youtube
    0.64
     Youtube
    0.64
     YouTube
    0.63
    Youtube
    0.55
    YouTube
    0.54
     यूट्यूब
    0.50
     유튜브
    0.50
     radio
    0.47
     радио
    0.47
    Activations Density 0.019%

    No Known Activations