© 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. 35339
    Prev
    Next
    INDEX
    Explanations

    his home

    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
     problemet
    -1.36
     sechs
    -1.21
    ,
    -1.20
     способ
    -1.17
     sieben
    -1.13
     neun
    -1.09
     startling
    -1.09
    _
    -1.09
    うれ
    -1.08
     $
    -1.05
    POSITIVE LOGITS
     home
    1.29
     by
    1.25
    ᐈ
    1.13
     before
    1.09
     after
    1.08
     verwendeten
    1.05
     convertido
    1.03
     menurun
    1.02
    位於
    1.02
     apartment
    1.01
    Activations Density 0.024%

    No Known Activations