© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117607
    Prev
    Next
    INDEX
    Explanations

    activities and skills

    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
    祠
    -0.87
     sobie
    -0.81
     같
    -0.76
    started
    -0.75
     szary
    -0.75
     getrock
    -0.74
     calentamiento
    -0.73
     Educate
    -0.73
    搞
    -0.72
    tiéndose
    -0.72
    POSITIVE LOGITS
     eating
    1.48
     eat
    1.43
     writing
    1.34
     drink
    1.30
     typing
    1.25
     cooking
    1.22
     tying
    1.21
     washing
    1.15
     opening
    1.13
     riding
    1.11
    Activations Density 0.133%

    No Known Activations