© 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. 202965
    Prev
    Next
    INDEX
    Explanations

    Rent, how, cooking, Trump

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

    weight loss constructed issue ear attempting

    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
    waffe
    0.45
    lensFlare
    0.45
    urrection
    0.44
    角
    0.42
     яку
    0.41
    boxyl
    0.40
    윅
    0.40
    clickHandler
    0.40
    niest
    0.39
     народу
    0.39
    POSITIVE LOGITS
     SAME
    0.48
     sağlay
    0.46
                              
    0.45
     Same
    0.43
                                  
    0.43
    CCI
    0.43
     soruml
    0.43
     füh
    0.43
     erken
    0.43
              
    0.42
    Activations Density 0.001%

    No Known Activations