© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 13916
    Prev
    Next
    INDEX
    Explanations

    javascript function definition

    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
    ಸ್
    0.44
    ล
    0.42
    sed
    0.41
    ಪ್
    0.41
    Encycl
    0.41
    о
    0.41
    னை
    0.39
    Charter
    0.39
    Ped
    0.39
    饞
    0.39
    POSITIVE LOGITS
     Україні
    0.46
    或
    0.44
     or
    0.42
    往往
    0.41
     vVertex
    0.41
     ανθρώ
    0.41
     infil
    0.40
     culture
    0.40
    ıldığı
    0.39
    的情况下
    0.39
    Activations Density 0.003%

    No Known Activations