© 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. 147543
    Prev
    Next
    INDEX
    Explanations

    political and economic terms

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

    saving further losses

    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
    Negative Logits
     vonat
    0.50
    갛
    0.44
    మో
    0.43
    $.\
    0.42
    CartVO
    0.42
    ﹟
    0.42
    }]}\
    0.41
    >();
    0.41
    multif
    0.41
    andra
    0.41
    POSITIVE LOGITS
     Teile
    0.52
    ラの
    0.50
     electromagnetic
    0.50
    κες
    0.47
    スの
    0.46
     Zusätzlich
    0.46
    ligere
    0.46
     Keynes
    0.46
     Поскольку
    0.46
     Lug
    0.45
    Activations Density 0.001%

    No Known Activations