© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109000
    Prev
    Next
    INDEX
    Explanations

    steel and alloys

    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
     venom
    -0.84
     "",
    -0.79
    目で
    -0.76
    ômes
    -0.75
    ディオ
    -0.74
    arbol
    -0.74
     ruim
    -0.73
    LOGGING
    -0.72
    אמ
    -0.70
     déroule
    -0.70
    POSITIVE LOGITS
     stainless
    2.58
     steel
    2.30
     brass
    2.27
     Stainless
    2.13
    Stainless
    1.82
     copper
    1.72
     Steel
    1.71
     steels
    1.65
    stainless
    1.64
     Brass
    1.63
    Activations Density 0.063%

    No Known Activations