© 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. 77581
    Prev
    Next
    INDEX
    Explanations

    weekly, department, insurance, transplant, page

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

    regulating behavior

    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
    鐒
    0.51
     Điều
    0.48
     சிதம்ப
    0.46
    нер
    0.46
    ához
    0.46
    펨
    0.46
    ถนน
    0.45
     массы
    0.44
     Stateless
    0.44
    锁
    0.44
    POSITIVE LOGITS
    vette
    0.53
     can
    0.53
    r
    0.51
    pay
    0.50
    し
    0.47
     teach
    0.47
    ]
    0.47
    \]
    0.46
     misinformation
    0.46
    phyll
    0.46
    Activations Density 0.001%

    No Known Activations