© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 97355
    Prev
    Next
    INDEX
    Explanations

    gentrification

    np_acts-logits-general · gemini-2.5-flash-lite

    life and development limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    0.56
     windows
    0.45
    imals
    0.45
    \
    0.44
     creep
    0.42
     add
    0.42
     flannel
    0.42
     butter
    0.41
    ี้
    0.41
     Material
    0.41
    POSITIVE LOGITS
     पाठ्यक्रमों
    0.54
     관계로
    0.54
    rocessor
    0.53
    rektor
    0.52
     giusta
    0.51
     سین
    0.50
     सनातन
    0.50
    ㄅ
    0.50
     ఏడాది
    0.50
     बबलू
    0.49
    Activations Density 0.000%

    No Known Activations