© 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. 63651
    Prev
    Next
    INDEX
    Explanations

    discouraging or deterring actions

    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
    NonNull
    -0.92
    TestingModule
    -0.87
     quà
    -0.85
    ჷ
    -0.84
     restlessness
    -0.83
     helplessness
    -0.82
    attere
    -0.81
     listView
    -0.80
     marlin
    -0.78
    iTunes
    -0.78
    POSITIVE LOGITS
     dissu
    3.16
     deter
    3.09
     discourage
    2.88
     deterred
    2.77
     deterrent
    2.72
     discouraged
    2.41
     discouraging
    2.36
     discou
    2.17
     deterrence
    2.08
     scare
    1.96
    Activations Density 0.050%

    No Known Activations