© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 64003
    Prev
    Next
    INDEX
    Explanations

    services that establish connections

    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
     önceki
    0.42
     পুরনো
    0.41
     Eastern
    0.40
    跹
    0.40
     للس
    0.39
     ধারাবাহিক
    0.39
     oposición
    0.38
    mrow
    0.37
     früheren
    0.37
    者的
    0.37
    POSITIVE LOGITS
    ermanfaat
    0.43
     comod
    0.39
     بتوان
    0.38
     dignissimos
    0.38
    iramente
    0.38
     반지름
    0.38
     Bona
    0.38
    ขนาด
    0.38
    ;
    0.38
    ranet
    0.37
    Activations Density 0.032%

    No Known Activations