© 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. 130465
    Prev
    Next
    INDEX
    Explanations

    list.setOnItemClickedListener

    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
    prende
    -0.95
     được
    -0.94
     these
    -0.88
    horts
    -0.88
     er
    -0.88
    ,
    -0.87
     "_
    -0.86
    が
    -0.84
    uudet
    -0.84
    strual
    -0.83
    POSITIVE LOGITS
     konsek
    1.04
     sanno
    1.01
    Harga
    1.00
    を探す
    0.99
    ganz
    0.98
     eccell
    0.98
     raccomand
    0.98
     leopardo
    0.96
    Jäh
    0.96
    ragende
    0.95
    Activations Density 0.186%

    No Known Activations