© 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. 4952
    Prev
    Next
    INDEX
    Explanations

    complex numerical calculations and produce the final sums or results based on various computations.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    numbers, calculations, and quantities

    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
    中医
    0.51
    母亲
    0.47
    Pyrimidine
    0.46
    👶
    0.46
    沬
    0.45
    Imidazole
    0.45
    语气
    0.45
    蝴
    0.44
    一来
    0.44
    肤
    0.44
    POSITIVE LOGITS
    9
    0.73
     
    0.68
    8
    0.68
     thousands
    0.67
     thousand
    0.66
    7
    0.64
    6
    0.63
    5
    0.62
     approximately
    0.61
     million
    0.60
    Activations Density 0.148%

    No Known Activations