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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100727
    Prev
    Next
    INDEX
    Explanations

    describing lengths, offerings, or changes

    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
     yuè
    0.41
     correlate
    0.41
     كيفية
    0.41
     ɖ
    0.41
     Simulate
    0.40
    போல்
    0.39
    的使用
    0.39
    ضور
    0.38
     intenso
    0.38
    ǃ
    0.38
    POSITIVE LOGITS
    รียน
    0.44
     బై
    0.42
    acijos
    0.41
    涣
    0.40
    ilise
    0.40
    ize
    0.40
     பொழுது
    0.40
    izzer
    0.40
    ையைக்
    0.39
    changes
    0.38
    Activations Density 0.005%

    No Known Activations