© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 7578
    Prev
    Next
    INDEX
    Explanations

    numerical values related to costs and calculations.

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

    money or 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
     Polar
    0.33
     אף
    0.32
    IsMethod
    0.32
     Plasma
    0.30
     พิจิก
    0.30
     Papa
    0.30
    ])/
    0.30
     Slice
    0.30
     Ku
    0.29
     Pius
    0.29
    POSITIVE LOGITS
    渠道
    0.32
    。
    0.31
    dollars
    0.31
    なので
    0.30
     barges
    0.30
     osób
    0.30
    那么
    0.29
     pouvant
    0.29
     persoane
    0.28
    ,
    0.28
    Activations Density 0.103%

    No Known Activations