© 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. 67150
    Prev
    Next
    INDEX
    Explanations

    sadness, tragedy, sorrow

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

    melancholy, sadness, tragedy

    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
    us
    0.64
    err
    0.63
    ol
    0.61
     you
    0.61
    ip
    0.59
    iv
    0.59
    ot
    0.58
    ’
    0.58
    ives
    0.58
    oids
    0.57
    POSITIVE LOGITS
     sorrow
    1.09
     triste
    1.08
     sadness
    1.04
    悲
    1.01
     tragic
    1.00
     heartbroken
    1.00
     melancholy
    0.98
     heartbreak
    0.96
     tristeza
    0.96
     plight
    0.95
    Activations Density 0.147%

    No Known Activations