© 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. 137081
    Prev
    Next
    INDEX
    Explanations

    perfect or good enough

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

    enemy of good

    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
     الصي
    0.48
    millan
    0.46
     Pathways
    0.44
     dígitos
    0.44
    stopwords
    0.43
     Ү
    0.43
    uesthouse
    0.43
    olda
    0.42
     pathways
    0.42
    arle
    0.42
    POSITIVE LOGITS
    จักร
    0.46
    قات
    0.44
    ≖
    0.43
    Other
    0.42
     دیگر
    0.42
     siêu
    0.42
    ーーーー
    0.42
    یدی
    0.42
    则是
    0.41
    𝑐
    0.41
    Activations Density 0.001%

    No Known Activations