© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118534
    Prev
    Next
    INDEX
    Explanations

    Bash script file path parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    quinone
    -0.84
    ]));
    -0.81
    chemy
    -0.80
     tome
    -0.77
     Cache
    -0.76
    deleted
    -0.74
     nécessaires
    -0.73
    CHANG
    -0.73
     Hed
    -0.72
     Kurs
    -0.71
    POSITIVE LOGITS
     woda
    0.97
     bautizo
    0.79
    Earlier
    0.77
     soffer
    0.77
     padx
    0.76
    envolvimento
    0.73
     gwar
    0.73
     {!
    0.73
     rootView
    0.72
    칫
    0.72
    Activations Density 0.006%

    No Known Activations