© 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. 162119
    Prev
    Next
    INDEX
    Explanations

    this and one

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

    disruption, values, or Hindi text

    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
     技术
    0.50
     বয়
    0.48
    一个月
    0.47
    avio
    0.47
     程序
    0.46
     图
    0.45
    Connecticut
    0.45
    滤
    0.43
    球队
    0.43
    𒁕
    0.43
    POSITIVE LOGITS
    л
    0.64
    イナー
    0.54
    б
    0.53
    grader
    0.51
     socialista
    0.51
    ul
    0.50
    (
    0.49
     popolare
    0.47
    др
    0.47
    ू
    0.47
    Activations Density 0.000%

    No Known Activations