© 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. 60004
    Prev
    Next
    INDEX
    Explanations

    fond, found, or fund

    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
    Condolences
    -0.82
    athic
    -0.79
    Lena
    -0.72
    していきます
    -0.71
    $};
    -0.71
    utes
    -0.70
    pocket
    -0.69
     appointe
    -0.69
    Esse
    -0.69
    Pd
    -0.68
    POSITIVE LOGITS
     Fond
    1.23
    fond
    1.19
     fonde
    1.09
     fond
    1.04
     FOUND
    1.03
     Founders
    1.02
    Fond
    1.00
    FOUND
    0.96
     founders
    0.95
    foundation
    0.94
    Activations Density 0.021%

    No Known Activations