© 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. 23555
    Prev
    Next
    INDEX
    Explanations

    legal citations and rules

    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
    TabStop
    -0.76
     sucul
    -0.74
    ghum
    -0.74
     schne
    -0.73
     costumi
    -0.73
    登陆
    -0.72
     ieri
    -0.71
     getEmail
    -0.71
    тах
    -0.70
     onore
    -0.70
    POSITIVE LOGITS
     angefangen
    0.86
    ICTION
    0.82
     почина
    0.79
     Tro
    0.78
     Konstruktion
    0.71
     начинается
    0.71
     Parti
    0.71
    生
    0.71
    MRI
    0.69
     Rains
    0.68
    Activations Density 0.028%

    No Known Activations