© 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. 81410
    Prev
    Next
    INDEX
    Explanations

    bandit, outlaw, robber

    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
     mực
    -0.74
    ocirc
    -0.72
    せば
    -0.72
    Lines
    -0.72
    bosity
    -0.71
    fehler
    -0.70
    ítez
    -0.70
    TypeError
    -0.69
    racism
    -0.68
    ][:
    -0.67
    POSITIVE LOGITS
     bandit
    1.80
     robber
    1.77
     robbers
    1.71
     highway
    1.70
     outlaw
    1.66
     robbery
    1.60
     thieves
    1.58
     bandits
    1.55
    Bandit
    1.48
     criminal
    1.46
    Activations Density 0.028%

    No Known Activations