© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28611
    Prev
    Next
    INDEX
    Explanations

    URLs and code delimiters

    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
    বা
    -1.08
    蛲
    -1.04
     Temperatura
    -1.02
    洶
    -1.02
    gården
    -1.00
    urals
    -1.00
    fiées
    -0.99
    面に
    -0.99
    welle
    -0.96
     Chambres
    -0.94
    POSITIVE LOGITS
     carefully
    1.15
     would
    1.08
    にしました
    1.03
    誰が
    1.02
     basically
    0.96
     closely
    0.96
     deliberately
    0.92
    complished
    0.91
     awkwardly
    0.90
     first
    0.90
    Activations Density 0.053%

    No Known Activations