© 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. 10-GEMMASCOPE-RES-131K
    7. 84388
    Prev
    Next
    INDEX
    Explanations

    Match scores and results

    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
    Not in Any Lists

    No Comments

    Negative Logits
     you
    -2.42
     already
    -1.99
     now
    -1.77
     currently
    -1.71
     years
    -1.59
     потому
    -1.57
     of
    -1.48
    Біографія
    -1.48
        
    -1.48
     recently
    -1.47
    POSITIVE LOGITS
     Despite
    1.41
     PÅ
    1.41
     GONNA
    1.36
    Kako
    1.34
    Despite
    1.33
    هه
    1.32
     почув
    1.32
     Apesar
    1.31
    >';
    1.30
    珍惜
    1.30
    Activations Density 0.007%

    No Known Activations