© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 147742
    Prev
    Next
    INDEX
    Explanations

    lost and found

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

    lost and found items

    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
    shallow
    0.40
     কলে
    0.40
    hbase
    0.38
    gnię
    0.38
    ಾರೆ
    0.37
    渤
    0.37
    珲
    0.37
    𒈥
    0.37
    ABIL
    0.36
    NewLine
    0.36
    POSITIVE LOGITS
     Lost
    0.57
     lost
    0.56
    Lost
    0.55
     LOST
    0.51
     recovers
    0.50
     Return
    0.49
     recoveries
    0.49
     Recover
    0.48
     finder
    0.47
     rejoicing
    0.47
    Activations Density 0.053%

    No Known Activations