© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112040
    Prev
    Next
    INDEX
    Explanations

    JSON object references

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

    references to JSONObject and JSONArray classes in programming code.

    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
    erder
    -1.40
    〟
    -1.38
    Schule
    -1.37
     celles
    -1.33
    骸
    -1.32
     eventuali
    -1.31
     品牌
    -1.27
    更多的
    -1.27
     have
    -1.27
     unterscheidet
    -1.27
    POSITIVE LOGITS
    关心
    1.63
    塒
    1.47
     logró
    1.46
    ᠂
    1.45
    ,
    1.44
    }$
    1.43
    name
    1.37
     ausreich
    1.34
    cdot
    1.34
    either
    1.33
    Activations Density 0.007%

    No Known Activations