© 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. 89712
    Prev
    Next
    INDEX
    Explanations

    bounty, bail, bond

    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
     narcissist
    -0.84
    ürger
    -0.77
     add
    -0.72
     survey
    -0.71
     input
    -0.69
    คม
    -0.69
     recount
    -0.69
    bekistan
    -0.68
     delimit
    -0.67
     protected
    -0.66
    POSITIVE LOGITS
     bail
    1.70
     bonds
    1.28
    bail
    1.25
     Bail
    1.25
     bonding
    1.18
     Bonds
    1.17
     Bonding
    1.11
    Bail
    1.10
     bond
    1.09
    bonding
    1.05
    Activations Density 0.008%

    No Known Activations