© 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. 28027
    Prev
    Next
    INDEX
    Explanations

    offers in

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

    workforce planning

    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
     causado
    0.53
     motivos
    0.52
     pierwsze
    0.51
     милли
    0.50
     канце
    0.49
     થી
    0.49
    嬌
    0.48
     conocido
    0.48
     ética
    0.47
     процессы
    0.47
    POSITIVE LOGITS
    T
    0.69
    on
    0.61
    s
    0.55
    act
    0.55
    en
    0.52
    L
    0.52
    l
    0.52
    dataloader
    0.50
    st
    0.49
     surpl
    0.49
    Activations Density 0.000%

    No Known Activations