© 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. 7348
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
     paco
    -1.69
     ila
    -1.57
     kazak
    -1.51
    izability
    -1.50
     kader
    -1.49
     heu
    -1.49
     kuni
    -1.48
     burch
    -1.46
     archite
    -1.45
     geene
    -1.45
    POSITIVE LOGITS
     use
    2.31
     your
    2.20
     and
    1.91
     give
    1.83
     find
    1.74
     take
    1.72
     try
    1.72
     ask
    1.69
     if
    1.69
     budete
    1.66
    Activations Density 0.013%

    No Known Activations