© 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. 76460
    Prev
    Next
    INDEX
    Explanations

    Become an, casualty, work it, search form

    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
    かせる
    -0.84
     rasg
    -0.82
     sosi
    -0.82
     aranha
    -0.82
    oxo
    -0.81
    ító
    -0.79
     язык
    -0.77
     maintenant
    -0.77
    сик
    -0.77
     algun
    -0.76
    POSITIVE LOGITS
     set
    1.00
     aggregate
    0.80
     Tuesday
    0.80
    ithub
    0.77
     honestly
    0.77
     almost
    0.77
    zystać
    0.77
     jump
    0.76
    ']==
    0.75
    ラベル
    0.75
    Activations Density 0.001%

    No Known Activations