© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3060
    Prev
    Next
    INDEX
    Explanations

    HM Prison, Naval, Queen

    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
    deau
    -0.79
     ago
    -0.77
     utilisation
    -0.75
     orbits
    -0.75
     optimised
    -0.74
    summary
    -0.74
     angu
    -0.74
    WebApplication
    -0.73
    spre
    -0.71
    aume
    -0.69
    POSITIVE LOGITS
     HM
    0.84
    蜚
    0.74
    nub
    0.71
     melanjutkan
    0.71
    یش
    0.70
     impresora
    0.68
    ATHY
    0.68
    spher
    0.67
    лайд
    0.67
     snabb
    0.67
    Activations Density 0.037%

    No Known Activations