© 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. 197625
    Prev
    Next
    INDEX
    Explanations

    you can tune

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

    threatens widespread job displacement

    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
    ınız
    0.46
    ruzzo
    0.46
    分区
    0.45
    erson
    0.44
    ículas
    0.44
     stabilized
    0.44
    老
    0.43
    ributions
    0.43
    ávez
    0.43
    ards
    0.43
    POSITIVE LOGITS
     сю
    0.49
     conten
    0.49
    tevõ
    0.47
     saddhim
    0.46
     被
    0.44
     assistência
    0.44
    linked
    0.44
     помощь
    0.44
    пря
    0.43
     تعط
    0.43
    Activations Density 0.000%

    No Known Activations