© 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. 77333
    Prev
    Next
    INDEX
    Explanations

    in the face 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
    しちゃ
    -1.27
    していますが
    -1.10
    しますね
    -0.92
    しましたが
    -0.92
     durabilidad
    -0.91
    過程中
    -0.91
     decoracion
    -0.89
     mây
    -0.86
    してきました
    -0.86
     consecuencia
    -0.86
    POSITIVE LOGITS
     of
    3.64
     revelations
    1.06
     increasing
    1.02
     thereof
    0.99
     của
    0.98
     ulteriori
    0.96
    pylab
    0.95
     его
    0.92
     rising
    0.91
     continued
    0.91
    Activations Density 0.018%

    No Known Activations