© 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. 34-GEMMASCOPE-RES-131K
    7. 70046
    Prev
    Next
    INDEX
    Explanations

    precision machining and prototyping

    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
    istika
    -0.88
    轮胎
    -0.86
    Newspaper
    -0.80
     کرت
    -0.79
    vesen
    -0.79
    琬
    -0.77
    berra
    -0.77
     ::=
    -0.77
    Extinguishing
    -0.77
    cement
    -0.76
    POSITIVE LOGITS
     precision
    1.55
     machining
    1.44
     prototype
    1.41
    precision
    1.35
     metal
    1.30
     prototyping
    1.27
     prototypes
    1.22
    prototype
    1.21
     aerospace
    1.20
    proto
    1.19
    Activations Density 0.053%

    No Known Activations