© 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-16K
    7. 12443
    Prev
    Next
    INDEX
    Explanations

    consequences of actions

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

    cost and sacrifice

    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_16k_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
    すが
    0.42
     asegurar
    0.41
    Refresh
    0.41
    んでいます
    0.41
    мина
    0.41
     持
    0.40
     державного
    0.40
     Seguridad
    0.39
     साइबर
    0.39
    哫
    0.39
    POSITIVE LOGITS
     unintended
    0.63
     inconvenience
    0.52
     merchants
    0.51
     affected
    0.50
     penal
    0.50
     merchant
    0.49
     businessmen
    0.48
     afecta
    0.48
     tourist
    0.47
     hardship
    0.46
    Activations Density 0.315%

    No Known Activations