© 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. 65729
    Prev
    Next
    INDEX
    Explanations

    following names and contexts

    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
     gestern
    -0.79
     Econ
    -0.79
    Integer
    -0.75
    Netflix
    -0.72
    Girl
    -0.71
     microphones
    -0.69
    最近
    -0.68
     孫
    -0.68
    horst
    -0.68
    toral
    -0.68
    POSITIVE LOGITS
     UNIVERSIT
    0.91
     Trumb
    0.89
    phen
    0.85
    特效
    0.82
    associate
    0.79
     Parameters
    0.79
     Effects
    0.79
     Umgang
    0.78
     effects
    0.77
    irsty
    0.77
    Activations Density 0.057%

    No Known Activations