© 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. 101242
    Prev
    Next
    INDEX
    Explanations

    method calls in code

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

    method calls or function invocations in programming code, particularly those involving output or system operations like `println`, `write`, `getElementById`, and `print`.

    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
     –
    -2.17
    5
    -1.98
    .
    -1.95
    :
    -1.92
     but
    -1.83
    大部分
    -1.68
    4
    -1.66
    ,
    -1.66
    If
    -1.65
    大家都
    -1.55
    POSITIVE LOGITS
     brinde
    1.72
     divertida
    1.71
     belangrijke
    1.67
    幛
    1.65
    唖
    1.64
    珦
    1.63
     animados
    1.63
     divertido
    1.63
    睨
    1.60
     encantador
    1.59
    Activations Density 0.001%

    No Known Activations