© 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. 63445
    Prev
    Next
    INDEX
    Explanations

    realizing something new

    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
     was
    -1.12
     would
    -1.02
     may
    -0.96
     need
    -0.93
     pihaknya
    -0.92
     ersch
    -0.91
     there
    -0.91
    惊
    -0.90
     interest
    -0.87
     kaufen
    -0.87
    POSITIVE LOGITS
     seeing
    1.66
     realizing
    1.66
     realize
    1.62
     realizes
    1.51
     realized
    1.48
     realising
    1.48
     realization
    1.46
     melihat
    1.44
     see
    1.43
     realise
    1.39
    Activations Density 0.043%

    No Known Activations