© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78617
    Prev
    Next
    INDEX
    Explanations

    someone's background

    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
    SG
    -0.86
    gania
    -0.81
     võimal
    -0.80
     lider
    -0.78
    apiVersion
    -0.78
    zonych
    -0.77
     ชั้น
    -0.76
    🦃
    -0.75
    nī
    -0.75
    znam
    -0.75
    POSITIVE LOGITS
     background
    6.06
     backgrounds
    4.97
    background
    4.63
     Background
    4.31
    Background
    4.22
     BACKGROUND
    3.59
    BACKGROUND
    3.45
    背景
    3.42
     Hintergrund
    2.89
     achtergrond
    2.83
    Activations Density 0.065%

    No Known Activations