© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103592
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    indented blocks of code, particularly within object or function definitions in JavaScript/TypeScript/JSON files.

    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
     also
    -2.44
     Also
    -1.80
    Also
    -1.70
     también
    -1.69
     or
    -1.64
     também
    -1.63
     Usually
    -1.55
     when
    -1.47
     Often
    -1.44
    Its
    -1.41
    POSITIVE LOGITS
     }).
    1.42
     }))
    1.38
     contempla
    1.34
     Meksiko
    1.32
     implica
    1.31
    idk
    1.30
     responsabili
    1.30
     reutiliz
    1.29
    Beantwoorden
    1.28
     incorpora
    1.28
    Activations Density 0.043%

    No Known Activations