© 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. 34-GEMMASCOPE-RES-131K
    7. 92070
    Prev
    Next
    INDEX
    Explanations

    List item preceding word

    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
    參見
    -0.82
     withstand
    -0.82
     дирек
    -0.81
     tamu
    -0.79
     ۱۵
    -0.78
     wagen
    -0.77
    一套
    -0.77
    емъ
    -0.76
    taban
    -0.75
     analogy
    -0.75
    POSITIVE LOGITS
    eye
    0.88
     crescente
    0.85
    user
    0.85
    两者
    0.85
     takım
    0.84
    𝒑
    0.84
     ngào
    0.83
    ごく
    0.82
     nzuri
    0.82
     buildings
    0.82
    Activations Density 0.006%

    No Known Activations