© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106720
    Prev
    Next
    INDEX
    Explanations

    use in various applications

    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_34/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
     each
    -1.41
     which
    -1.38
     every
    -1.29
     from
    -1.20
     hébergement
    -1.16
     immerhin
    -1.06
    んだよね
    -1.05
     all
    -1.01
    کند
    -0.97
    出来た
    -0.96
    POSITIVE LOGITS
     where
    1.85
     requiring
    1.74
     especially
    1.66
     because
    1.59
     karena
    1.55
     needing
    1.51
    especially
    1.48
    ต้องการ
    1.48
    where
    1.46
    因为
    1.46
    Activations Density 0.188%

    No Known Activations