© 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. 43945
    Prev
    Next
    INDEX
    Explanations

    blaming for crimes and liability

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

    statistics, parasites, store, weights

    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
     አንዳንድ
    0.47
     जोड़ों
    0.46
    YE
    0.44
    ਭ
    0.44
    inputSelect
    0.44
    kező
    0.43
     সফরে
    0.43
    marginX
    0.42
    тельные
    0.41
     そ
    0.41
    POSITIVE LOGITS
     aggrieved
    0.53
     blames
    0.52
     crimes
    0.51
     culpable
    0.49
     epidemiology
    0.48
     mercantil
    0.48
     prosecutors
    0.47
     blame
    0.47
     culp
    0.46
     for
    0.46
    Activations Density 0.000%

    No Known Activations