© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110672
    Prev
    Next
    INDEX
    Explanations

    instantiating programming objects

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

    PHP class names and constructor calls, particularly those related to date/time, DOM, and PDO objects.

    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
    на
    -1.50
     понадоби
    -1.39
     הראשון
    -1.36
     scris
    -1.34
     mesmos
    -1.34
    ן
    -1.33
     Schritte
    -1.33
     făcut
    -1.32
     будет
    -1.31
    癀
    -1.29
    POSITIVE LOGITS
     you
    1.89
     have
    1.47
     that
    1.47
    CHREIB
    1.41
    韡
    1.40
     our
    1.39
     by
    1.36
     even
    1.34
     }
    1.34
    ÍTICA
    1.32
    Activations Density 0.022%

    No Known Activations