© 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. 103631
    Prev
    Next
    INDEX
    Explanations

    childhood sweetheart

    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
    feedback
    -0.79
    IRQn
    -0.77
    ẩm
    -0.76
    exif
    -0.75
    wną
    -0.75
    wają
    -0.75
    lesssim
    -0.74
     Prestige
    -0.73
     Asylum
    -0.73
    имость
    -0.73
    POSITIVE LOGITS
     crush
    4.88
    crush
    3.78
     Crush
    3.73
     crushes
    3.69
    Crush
    3.53
     crushing
    2.97
     crushed
    2.64
     Crus
    2.36
     crusher
    2.27
    Crus
    1.89
    Activations Density 0.023%

    No Known Activations