© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49355
    Prev
    Next
    INDEX
    Explanations

    actions followed by of

    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
    bö
    -1.00
    屨
    -1.00
    alcool
    -0.97
     comprando
    -0.96
    vidades
    -0.95
     cerveza
    -0.93
     cerâmica
    -0.93
    nourriture
    -0.93
    感じが
    -0.92
    厛
    -0.91
    POSITIVE LOGITS
     of
    4.22
     or
    1.50
     by
    1.48
     thereof
    0.98
    ᐈ
    0.90
     носить
    0.90
     complained
    0.88
    ของ
    0.87
    angulaire
    0.85
    ichni
    0.85
    Activations Density 0.111%

    No Known Activations