© 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. 220647
    Prev
    Next
    INDEX
    Explanations

    launched on, lost twice, long distance

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

    grief discomfort intentions

    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
    -
    0.53
    5
    0.51
    d
    0.50
    (
    0.48
    each
    0.48
     squares
    0.47
    s
    0.46
    0
    0.45
     knock
    0.45
    t
    0.45
    POSITIVE LOGITS
     transformación
    0.58
     Çocuk
    0.55
    וד
    0.55
    ਪਣ
    0.54
     conversación
    0.54
     потребности
    0.53
    艐
    0.53
     ihtiyaç
    0.52
     ఇటీవల
    0.52
     ఇటీ
    0.52
    Activations Density 0.001%

    No Known Activations