© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 45695
    Prev
    Next
    INDEX
    Explanations

    time descriptions and services

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

    legal act. design. accumulated. actively. fact. nothing. manual burden

    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
    kl
    0.62
    in
    0.53
    add
    0.51
    ess
    0.50
    est
    0.48
    wo
    0.48
    :{
    0.48
    t
    0.48
    su
    0.48
    k
    0.47
    POSITIVE LOGITS
     werken
    0.54
     trabajo
    0.52
     poświę
    0.52
     kerja
    0.51
     écologique
    0.50
     trabaj
    0.50
     trabalho
    0.50
    ﺭ
    0.50
     lavoro
    0.50
     adecuados
    0.49
    Activations Density 0.000%

    No Known Activations