© 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. 108351
    Prev
    Next
    INDEX
    Explanations

    intermediate followed by a category

    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
     杨
    -0.81
    อีก
    -0.80
    看着
    -0.79
    Configured
    -0.76
    "{\
    -0.76
    cumin
    -0.74
    iriman
    -0.73
    cook
    -0.73
    Another
    -0.73
    غم
    -0.73
    POSITIVE LOGITS
     steps
    1.25
     Intermediate
    1.13
     stages
    1.09
    相遇
    1.03
     between
    1.02
    Intermediate
    1.02
    intermediate
    1.00
     intermediate
    0.98
    andina
    0.90
     step
    0.90
    Activations Density 0.021%

    No Known Activations