© 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. 47116
    Prev
    Next
    INDEX
    Explanations

    time and subsequent words

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

    multi-word phrases/collocations

    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
    वा
    0.52
    axies
    0.48
    目标
    0.48
     调用
    0.48
    时
    0.47
     被
    0.46
    ленд
    0.46
    Liberty
    0.46
    tained
    0.46
    рати
    0.46
    POSITIVE LOGITS
     Wahrheit
    0.46
    のない
    0.45
     선생
    0.44
     falso
    0.43
     scris
    0.43
     selepas
    0.43
    ncnc
    0.42
     黒
    0.41
    指摘
    0.41
     elektron
    0.41
    Activations Density 0.000%

    No Known Activations