© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65974
    Prev
    Next
    INDEX
    Explanations

    loss and deterioration

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

    The neuron strongly detects occurrences of “waste” and its inflected forms (especially “wasted” and “wasting”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    涐
    -2.73
    ﻂ
    -2.67
    
    -2.53
    
    -2.44
    小時
    -2.44
    ية
    -2.41
    肏
    -2.39
     Projektu
    -2.39
     اهم
    -2.33
    齣
    -2.31
    POSITIVE LOGITS
     in
    2.77
    鴣
    2.69
    these
    2.69
     That
    2.38
    a
    2.30
     These
    2.23
     $
    2.20
     To
    2.19
    that
    2.19
     que
    2.09
    Activations Density 0.002%

    No Known Activations