© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58224
    Prev
    Next
    INDEX
    Explanations

    common challenges and solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     bordering
    -1.66
     Thankfully
    -1.64
    4
    -1.60
     Obviously
    -1.55
     trochę
    -1.55
     bestowed
    -1.54
     them
    -1.54
    ).
    -1.49
    ってみました
    -1.47
     maravilh
    -1.46
    POSITIVE LOGITS
     parfüm
    2.05
    #%%
    1.76
     宣传
    1.74
    앰
    1.74
    ##############
    1.70
     denkt
    1.70
    ➡
    1.67
     flesta
    1.67
     sokak
    1.66
    饧
    1.66
    Activations Density 24.670%

    No Known Activations