© 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. 76013
    Prev
    Next
    INDEX
    Explanations

    software, hardware, plugins

    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
    ੧
    -0.74
    してみると
    -0.72
    一瞬
    -0.67
     acelerar
    -0.66
    ciosa
    -0.65
    していますが
    -0.65
    gok
    -0.65
    也太
    -0.64
     Vere
    -0.64
     tồn
    -0.64
    POSITIVE LOGITS
    Manip
    0.93
     Packages
    0.92
    节点
    0.88
     manipulator
    0.87
     hardware
    0.84
     nodes
    0.82
    CHER
    0.82
     Competitions
    0.82
     Nodes
    0.81
    SETTINGS
    0.81
    Activations Density 0.020%

    No Known Activations