© 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. 2041
    Prev
    Next
    INDEX
    Explanations

    char pointer or buffer

    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
     catalán
    -1.10
    热闹
    -0.94
     réus
    -0.94
     doulou
    -0.93
     完了
    -0.92
     extranjero
    -0.91
     mystérie
    -0.91
     áudio
    -0.90
     Aktivitäten
    -0.89
     couvre
    -0.89
    POSITIVE LOGITS
    *
    1.55
     buf
    1.11
    .*;
    1.05
    []
    1.01
     *
    1.01
     pady
    0.98
    ően
    0.98
     '\''
    0.98
    msgstr
    0.98
     [''],
    0.97
    Activations Density 0.005%

    No Known Activations