© 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. 59420
    Prev
    Next
    INDEX
    Explanations

    affecting outcomes and scope

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

    global variables

    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
    কেউ
    0.48
     অথবা
    0.44
    लोग
    0.43
     Agencies
    0.43
    區
    0.42
    或
    0.42
    ៕
    0.41
     hoặc
    0.40
    関
    0.40
    壬
    0.40
    POSITIVE LOGITS
     detrimental
    0.43
     perjury
    0.42
     می‌کند
    0.39
     힘들
    0.39
     hvil
    0.38
     inductively
    0.38
    ඩා
    0.37
     dangerous
    0.37
     undue
    0.37
     definitiva
    0.37
    Activations Density 0.000%

    No Known Activations