© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48925
    Prev
    Next
    INDEX
    Explanations

    mines and explosives

    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
     pār
    -0.78
     turnovers
    -0.72
    partials
    -0.71
     város
    -0.70
    avao
    -0.68
    暉
    -0.68
    expre
    -0.68
    亨
    -0.67
    arão
    -0.66
     Last
    -0.65
    POSITIVE LOGITS
     mines
    3.13
     mine
    2.77
    mines
    2.30
    Mine
    2.30
    Mines
    2.20
    mine
    2.13
     Mines
    2.09
     Mine
    2.05
     mined
    2.05
     MINE
    1.80
    Activations Density 0.022%

    No Known Activations