© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79660
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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_262k_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
     میشه
    0.58
     następnie
    0.54
    镛
    0.50
    优点
    0.49
    亼
    0.49
     میشود
    0.49
    机器
    0.49
     pozwala
    0.49
     amélior
    0.49
    设计
    0.48
    POSITIVE LOGITS
     perished
    0.57
     risked
    0.53
     Venezuela
    0.52
     calamities
    0.49
    <0xAA>
    0.47
     threatened
    0.47
     Somalia
    0.47
     около
    0.47
     amenaza
    0.47
     緊急
    0.45
    Activations Density 0.004%

    No Known Activations