© 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. 181365
    Prev
    Next
    INDEX
    Explanations

    employment and applications

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

    solar panels

    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
     dô
    0.51
     lộ
    0.48
     nhiêu
    0.42
    存在
    0.41
     mercur
    0.41
    波动
    0.40
    麪
    0.40
     betray
    0.39
    ᱼ
    0.39
     thước
    0.39
    POSITIVE LOGITS
    یمو
    0.55
    applicants
    0.52
    برای
    0.51
    apprentissage
    0.51
     achievable
    0.51
    زش
    0.50
    िक
    0.49
     Isid
    0.49
    등
    0.48
    別の
    0.48
    Activations Density 0.001%

    No Known Activations