© 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. 39359
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
     reconocido
    -1.16
     reconocidos
    -1.09
    )));
    -0.96
    pretation
    -0.95
    ER
    -0.95
    ModelAdmin
    -0.95
    out
    -0.94
     "
    -0.94
    บค
    -0.92
    cenary
    -0.92
    POSITIVE LOGITS
    źnie
    1.20
     油画
    1.17
    鈑
    1.11
     annuel
    1.10
    arraycopy
    1.09
    ooooo
    1.06
    犷
    1.04
     firstly
    1.03
    yyyyy
    1.03
    hoku
    1.02
    Activations Density 0.066%

    No Known Activations