© 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. 720
    Prev
    Next
    INDEX
    Explanations

    juice and juicy things

    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
    thesis
    -0.88
    __:
    -0.83
     troubled
    -0.81
    easter
    -0.79
    ajoz
    -0.77
    inut
    -0.77
    ;"><
    -0.76
    iddler
    -0.75
    Lng
    -0.74
     dòng
    -0.74
    POSITIVE LOGITS
     Ju
    1.04
     Juice
    1.00
    Ju
    0.88
    box
    0.87
     JU
    0.85
     ransomware
    0.85
     juice
    0.84
     oranges
    0.82
    ヴ
    0.82
     Lucy
    0.79
    Activations Density 0.007%

    No Known Activations