© 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. 116071
    Prev
    Next
    INDEX
    Explanations

    kids, women, or world

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

    code, documentation, or technical terms

    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
     書き
    0.47
    ਣ
    0.47
     って
    0.47
     使っ
    0.46
     ነው።
    0.46
     ない
    0.45
    って
    0.45
    いや
    0.45
     obie
    0.45
     datth
    0.45
    POSITIVE LOGITS
    Configurations
    0.51
     MODIFY
    0.49
    ids
    0.41
    语
    0.41
     alterations
    0.40
    模仿
    0.40
    圆形
    0.40
    调度
    0.39
     waveforms
    0.39
    多样
    0.39
    Activations Density 0.000%

    No Known Activations