© 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. 22-GEMMASCOPE-RES-131K
    7. 34497
    Prev
    Next
    INDEX
    Explanations

    mathematical expression `h**`

    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
    usaha
    -1.08
    ctober
    -1.03
     olvidado
    -1.00
     him
    -0.97
     február
    -0.96
    mohon
    -0.95
    karakter
    -0.95
    daun
    -0.94
    thday
    -0.93
    fokus
    -0.92
    POSITIVE LOGITS
     sàng
    1.09
    たしか
    1.06
     erfordert
    1.05
    就可以了
    1.05
     integrand
    1.02
     beruht
    1.02
     einsetzen
    1.01
    確かに
    1.01
     Indones
    0.98
     benefici
    0.97
    Activations Density 0.011%

    No Known Activations