© 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. 83212
    Prev
    Next
    INDEX
    Explanations

    bond and guarantees

    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
    jard
    -0.73
     testifying
    -0.71
    âteaux
    -0.71
    eaway
    -0.70
     informacji
    -0.69
     autorytatywna
    -0.68
     lends
    -0.67
    الإنجليزية
    -0.67
    arning
    -0.66
    高級
    -0.66
    POSITIVE LOGITS
     bond
    2.39
     bonding
    2.14
    bonding
    1.86
     bonds
    1.84
    Bond
    1.81
     Bond
    1.77
    bond
    1.72
     Bonding
    1.70
     bonded
    1.69
     BOND
    1.63
    Activations Density 0.014%

    No Known Activations