© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131673
    Prev
    Next
    INDEX
    Explanations

    privilege escalation

    np_acts-logits-general · gemini-2.5-flash-lite

    lens properties, ume plums, world must

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comedian
    0.52
    ('@
    0.48
     chinois
    0.45
     inventory
    0.45
     expense
    0.44
    Inspector
    0.44
     pedigree
    0.43
    ዠ
    0.43
     wholesaler
    0.42
    Կ
    0.42
    POSITIVE LOGITS
     autón
    0.47
     Lucid
    0.46
     transmisión
    0.45
     Mits
    0.45
    ún
    0.44
    روح
    0.44
    passt
    0.44
     Deleg
    0.44
     autonom
    0.43
    gelt
    0.43
    Activations Density 0.000%

    No Known Activations