© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91239
    Prev
    Next
    INDEX
    Explanations

    guided walking tours

    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
    Camping
    -0.91
     Nordrhein
    -0.81
    CTIONS
    -0.80
     uč
    -0.79
     resort
    -0.79
     гипер
    -0.79
     Camping
    -0.78
     giocare
    -0.78
     camping
    -0.77
    مزید
    -0.76
    POSITIVE LOGITS
     walking
    1.92
     guided
    1.92
     tour
    1.83
     tours
    1.74
    walking
    1.48
     Guided
    1.42
    Walking
    1.39
    guided
    1.39
     Walking
    1.37
     walks
    1.34
    Activations Density 0.014%

    No Known Activations