© 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. 45356
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and ownership notices

    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
     Diret
    -0.85
     erfolgre
    -0.82
     residen
    -0.77
     umane
    -0.75
     Workstation
    -0.75
     duong
    -0.75
     catto
    -0.73
    鵯
    -0.73
     AGRIC
    -0.72
    サード
    -0.70
    POSITIVE LOGITS
     applause
    0.83
    𝘗
    0.75
     Translation
    0.73
     Lima
    0.72
     Sally
    0.69
    zsche
    0.69
    NEP
    0.69
    +</
    0.68
    ша
    0.68
     Cong
    0.67
    Activations Density 0.023%

    No Known Activations