© 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. 154430
    Prev
    Next
    INDEX
    Explanations

    lowest stellar masses

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

    changing situations

    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
    encement
    0.46
    埂
    0.45
    udere
    0.45
     براي
    0.44
    ريبات
    0.44
    athyroid
    0.43
     ২৩
    0.42
    ب
    0.41
    呂
    0.41
    اي
    0.40
    POSITIVE LOGITS
     transferable
    0.43
    matched
    0.43
    increasing
    0.43
    leader
    0.42
    ジア
    0.42
    шили
    0.41
    stripped
    0.41
     değişt
    0.41
     dobra
    0.40
    logos
    0.39
    Activations Density 0.001%

    No Known Activations