© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89858
    Prev
    Next
    INDEX
    Explanations

    red, blue, white followed by name

    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
    膦
    -0.75
     crowned
    -0.74
     स्ट
    -0.73
    力の
    -0.72
    苯
    -0.72
     Markets
    -0.71
    діть
    -0.71
    技巧
    -0.71
     Sty
    -0.70
    saison
    -0.69
    POSITIVE LOGITS
     різних
    0.79
     edit
    0.77
    രി
    0.74
    ocie
    0.73
    ええ
    0.69
     Groupe
    0.69
     atheists
    0.68
    क्षण
    0.66
    edit
    0.66
     edits
    0.65
    Activations Density 0.031%

    No Known Activations