© 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. 122579
    Prev
    Next
    INDEX
    Explanations

    laws, agreements, and research

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

    simple case, short meeting, broad overviews

    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
    0.58
     resident
    0.47
     Resident
    0.46
    Resident
    0.46
     enacted
    0.44
     clergyman
    0.42
    resident
    0.42
     systemat
    0.42
    j
    0.42
    ras
    0.41
    POSITIVE LOGITS
    ১২শ
    0.50
    훑
    0.49
    klady
    0.49
     الاقتصاد
    0.48
    糍
    0.48
    ᅯ
    0.47
    ducation
    0.47
    મિ
    0.46
     rohkem
    0.46
    𝔻
    0.46
    Activations Density 0.000%

    No Known Activations