© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102724
    Prev
    Next
    INDEX
    Explanations

    type casting and checking

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

    the keyword "instanceof" in programming code for type checking or class instance verification.

    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
     meestal
    -1.63
     was
    -1.45
     which
    -1.45
    zeniu
    -1.45
     whose
    -1.44
     &
    -1.34
     whom
    -1.34
    _
    -1.31
     waarschijnlijk
    -1.31
    -
    -1.30
    POSITIVE LOGITS
    acterísticas
    2.16
    𓆟
    1.87
    媖
    1.79
    </h2>
    1.77
    陞
    1.69
     solchen
    1.68
     Hinblick
    1.62
    __':
    1.62
    ądze
    1.61
    ffine
    1.59
    Activations Density 0.002%

    No Known Activations