© 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. 45739
    Prev
    Next
    INDEX
    Explanations

    career achievements

    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
     potential
    -0.88
    빠
    -0.85
    potential
    -0.79
     llevaron
    -0.78
     quedaron
    -0.76
    liefert
    -0.73
     struct
    -0.72
     your
    -0.72
    ŵ
    -0.70
     conditions
    -0.69
    POSITIVE LOGITS
     distinguished
    2.19
     illustrious
    1.98
     decorated
    1.66
     stor
    1.56
    stellar
    1.46
     illust
    1.44
     impressive
    1.37
     Illust
    1.37
     illustre
    1.30
     stellar
    1.27
    Activations Density 0.058%

    No Known Activations