© 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. 22-GEMMASCOPE-RES-131K
    7. 25339
    Prev
    Next
    INDEX
    Explanations

    showcasing abilities and qualities

    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_22/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
     Dö
    -0.96
     всегда
    -0.88
    lillah
    -0.86
     zawsze
    -0.84
     treble
    -0.83
     Goed
    -0.83
    entlichen
    -0.81
     vestir
    -0.80
     améli
    -0.80
    ник
    -0.80
    POSITIVE LOGITS
     by
    1.46
     again
    1.19
     demonstrated
    1.18
    Kā
    1.09
     demuestra
    1.09
     when
    1.08
     demonstrate
    1.07
     through
    1.06
     demostrar
    1.02
    Переваги
    0.99
    Activations Density 0.045%

    No Known Activations