© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48395
    Prev
    Next
    INDEX
    Explanations

    display text and strings

    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_34/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
    sive
    -0.77
     '".$
    -0.77
     walkway
    -0.73
    煨
    -0.73
    dcmdata
    -0.72
    ллер
    -0.72
     löytyy
    -0.72
    薅
    -0.71
     '=
    -0.71
    écriture
    -0.71
    POSITIVE LOGITS
     text
    1.01
     color
    0.95
     Text
    0.88
     Prata
    0.82
     colour
    0.79
    Text
    0.77
     formatting
    0.77
    縮
    0.76
     tokens
    0.76
     localisation
    0.75
    Activations Density 0.028%

    No Known Activations