© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104220
    Prev
    Next
    INDEX
    Explanations

    mathematical implication or code structure

    np_acts-logits-general · gemini-2.5-flash-lite

    code syntax elements, particularly function calls, method invocations, and mathematical implication symbols.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    阄
    -3.16
    觏
    -3.03
     expériment
    -2.69
    떳
    -2.64
    ኧ
    -2.59
    薆
    -2.58
    नलोड
    -2.50
    〤
    -2.48
    憮
    -2.48
    ⎔
    -2.45
    POSITIVE LOGITS
    夀
    2.64
    -
    2.61
     可以
    2.61
     builds
    2.41
    z
    2.31
     caters
    2.28
    釹
    2.28
    ar
    2.28
     —
    2.27
    in
    2.25
    Activations Density 0.002%

    No Known Activations