© 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. 10-GEMMASCOPE-RES-131K
    7. 12003
    Prev
    Next
    INDEX
    Explanations

    reflect on

    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_10/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
     almeno
    -2.00
     neuen
    -1.86
    ᆞ
    -1.85
    籏
    -1.85
     signifikan
    -1.84
    鯷
    -1.79
     เห
    -1.79
     Hacer
    -1.76
    🕗
    -1.75
    轳
    -1.74
    POSITIVE LOGITS
     
    2.17
     “
    1.96
     on
    1.88
    ...
    1.73
    ie
    1.73
    s
    1.60
    “
    1.58
    an
    1.55
     no
    1.54
     ;
    1.52
    Activations Density 0.005%

    No Known Activations