© 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. 245783
    Prev
    Next
    INDEX
    Explanations

    promote overall, pursue the

    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
    طي
    0.58
    حي
    0.50
    عات
    0.49
    طم
    0.49
    يع
    0.46
    فير
    0.46
    f
    0.46
    មាន
    0.45
    بيق
    0.45
    يط
    0.45
    POSITIVE LOGITS
     ながら
    0.52
    porque
    0.47
     Sey
    0.47
     prioritization
    0.47
    alist
    0.46
     こ
    0.46
     categorization
    0.46
     アウトドア
    0.46
    āya
    0.46
    ajou
    0.46
    Activations Density 0.001%

    No Known Activations