© 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. 219056
    Prev
    Next
    INDEX
    Explanations

    ephemeral renown rumours transient

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

    good hopeful friendly

    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
    s
    0.44
    pry
    0.44
    ydd
    0.43
    k
    0.43
    RD
    0.43
     সাথেই
    0.41
    NOWLEDGE
    0.41
    kys
    0.41
    o
    0.40
    roll
    0.40
    POSITIVE LOGITS
     ephemeral
    0.51
    ؟
    0.50
     renown
    0.49
     latar
    0.49
     rumours
    0.49
    لة
    0.48
     notoriety
    0.48
    Transient
    0.47
     membrana
    0.46
     IAA
    0.46
    Activations Density 0.002%

    No Known Activations