© 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. 76018
    Prev
    Next
    INDEX
    Explanations

    prison or jail

    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
    PROFILE
    -0.88
     dreamstime
    -0.83
    хані
    -0.82
     punte
    -0.79
     Macintosh
    -0.77
    profile
    -0.77
     bilde
    -0.76
     uruguay
    -0.75
    čeno
    -0.74
    sier
    -0.74
    POSITIVE LOGITS
     jail
    5.41
     prison
    5.16
     Jail
    3.69
    jail
    3.63
     Prison
    3.63
     prisons
    3.56
    prison
    3.52
    Jail
    3.34
    Prison
    3.25
     jails
    3.19
    Activations Density 0.049%

    No Known Activations