© 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. 73378
    Prev
    Next
    INDEX
    Explanations

    version 3

    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
     people
    -0.76
     getItemCount
    -0.69
     constructing
    -0.69
    场合
    -0.68
    advanced
    -0.68
     forming
    -0.66
    áncer
    -0.65
    tisol
    -0.64
     constructs
    -0.64
     continual
    -0.64
    POSITIVE LOGITS
     QUAL
    0.78
     boycot
    0.74
    kose
    0.73
     SOCIAL
    0.73
    ramo
    0.71
    ✣
    0.71
    enig
    0.71
     Sputnik
    0.69
     IDS
    0.68
     buoyancy
    0.68
    Activations Density 0.086%

    No Known Activations