© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20900
    Prev
    Next
    INDEX
    Explanations

    new sentence start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    োনাম
    0.48
    ="
    0.47
     যথা
    0.47
    、
    0.47
    「
    0.46
     Veuillez
    0.44
    （
    0.44
    ικές
    0.43
     пожалуйста
    0.42
     grasped
    0.42
    POSITIVE LOGITS
     दरअसल
    0.54
     जिससे
    0.48
     அந்த
    0.48
     এরপর
    0.47
     जिसे
    0.45
     गौरतलब
    0.45
    ਬ
    0.44
     જેમાં
    0.44
     경우
    0.43
     द्वार
    0.42
    Activations Density 0.004%

    No Known Activations