© 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. 14614
    Prev
    Next
    INDEX
    Explanations

    describing excellence and special qualities

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

    describing excellence and beauty

    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
     shitty
    0.80
    😡
    0.74
     fucking
    0.71
     idk
    0.69
    😑
    0.69
    そもそも
    0.69
     merda
    0.68
    😐
    0.65
     nějak
    0.64
    🫤
    0.63
    POSITIVE LOGITS
     unsurpassed
    0.95
     unrivalled
    0.84
     exhilarating
    0.82
     richly
    0.71
     unparalleled
    0.71
     superbly
    0.69
     unforgettable
    0.66
     renowned
    0.65
     exquisitely
    0.64
     uniquely
    0.63
    Activations Density 0.245%

    No Known Activations