© 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. 75700
    Prev
    Next
    INDEX
    Explanations

    South followed by location or direction

    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
    証拠
    -0.92
    そうですが
    -0.84
     mercados
    -0.84
    彼女は
    -0.84
    录取
    -0.82
    ショップ
    -0.81
    遵循
    -0.81
    職場
    -0.81
     modalidades
    -0.80
    Tja
    -0.79
    POSITIVE LOGITS
    ward
    1.17
     Carolina
    1.10
    bound
    1.09
    rons
    1.09
     Korean
    1.06
     Korea
    1.04
     African
    1.02
     ''
    
    1.02
    side
    1.02
    paw
    1.00
    Activations Density 0.031%

    No Known Activations