© 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-262K
    7. 138745
    Prev
    Next
    INDEX
    Explanations

    definitions of technical terms

    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_262k_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
    vs
    0.47
    ↵↵
    0.47
     vs
    0.47
     Provides
    0.46
    /
    0.43
    5
    0.42
     Functions
    0.42
    Audio
    0.41
    ation
    0.40
    uration
    0.40
    POSITIVE LOGITS
    同样
    0.48
    ند
    0.46
     sección
    0.46
     пор
    0.45
    也是
    0.44
     يا
    0.43
     напа
    0.42
    有两种
    0.40
    同樣
    0.40
    亦
    0.40
    Activations Density 0.051%

    No Known Activations