© 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. 180661
    Prev
    Next
    INDEX
    Explanations

    foreign and technical terms

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

    requirements, future, websites, multiple, allowing, ivy, gym

    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
    user
    0.48
    टे
    0.46
    azioni
    0.46
    November
    0.46
    warming
    0.46
    𝐬
    0.46
    গোষ্ঠ
    0.46
     niño
    0.45
    ativas
    0.45
     तथ्य
    0.45
    POSITIVE LOGITS
    בּ
    0.47
    xRt
    0.47
    锻
    0.46
     modification
    0.45
     ermöglichen
    0.45
     filled
    0.45
     described
    0.45
    嫖
    0.45
     FEC
    0.44
     ಪೊಲೀಸ
    0.44
    Activations Density 0.000%

    No Known Activations