© 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. 100570
    Prev
    Next
    INDEX
    Explanations

    XML attributes and code objects

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

    the suffix "AsString" in method names and variable identifiers in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires on identifier tokens containing the substring “as” (e.g. attrs, AsString, ReadAsStringAsync).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ↵
    -3.27
     was
    -2.94
    媗
    -2.78
    a
    -2.77
    $
    -2.63
    e
    -2.53
    </em>
    -2.52
    缡
    -2.36
    𓋼
    -2.34
    !”
    -2.28
    POSITIVE LOGITS
    啬
    2.69
                    
    2.61
    बाइल
    2.45
    你是不是
    2.36
     When
    2.23
    奥运
    2.19
    鉿
    2.19
    不错
    2.19
    小时候
    2.19
    庒
    2.16
    Activations Density 0.001%

    No Known Activations